Commit
•
3909518
1
Parent(s):
27e0581
Upload PPO LunarLander-v2 trained agent
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/_stable_baselines3_version +1 -1
- ppo-LunarLander-v2/data +49 -45
- ppo-LunarLander-v2/policy.optimizer.pth +1 -1
- ppo-LunarLander-v2/policy.pth +2 -2
- ppo-LunarLander-v2/system_info.txt +6 -4
- replay.mp4 +2 -2
- results.json +1 -1
README.md
CHANGED
@@ -16,7 +16,7 @@ model-index:
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value: -
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: -176.74 +/- 83.90
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7fc037fae0d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc037fae160>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc037fae1f0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc037fae280>", "_build": "<function ActorCriticPolicy._build at 0x7fc037fae310>", "forward": "<function ActorCriticPolicy.forward at 0x7fc037fae3a0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fc037fae430>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc037fae4c0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fc037fae550>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc037fae5e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc037fae670>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc037fae700>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fc037fadfc0>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 16384, "_total_timesteps": 1000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1678910094329777351, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -15.384, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 4, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "gAWVwwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOS9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4JDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOS9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/yZmZmZmZmoWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.9.16", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu116", "GPU Enabled": "True", "Numpy": "1.22.4", "Gym": "0.21.0"}}
|
|
|
1 |
+
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7f5bc9451750>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f5bc94517e0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f5bc9451870>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f5bc9451900>", "_build": "<function ActorCriticPolicy._build at 0x7f5bc9451990>", "forward": "<function ActorCriticPolicy.forward at 0x7f5bc9451a20>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f5bc9451ab0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f5bc9451b40>", "_predict": "<function ActorCriticPolicy._predict at 0x7f5bc9451bd0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f5bc9451c60>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f5bc9451cf0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f5bc9451d80>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f5bc945c340>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 16384, "_total_timesteps": 1000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1683116033505747256, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -15.384, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 5, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True True True True True]", "bounded_above": "[ True True True True True True True True]", "_shape": [8], "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.10.11", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.0+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
ppo-LunarLander-v2.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:597452a49dea13008271f0acba9e0fa80ef23b940239835130a10b7988902aaf
|
3 |
+
size 146602
|
ppo-LunarLander-v2/_stable_baselines3_version
CHANGED
@@ -1 +1 @@
|
|
1 |
-
|
|
|
1 |
+
2.0.0a5
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,60 +4,34 @@
|
|
4 |
":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
5 |
"__module__": "stable_baselines3.common.policies",
|
6 |
"__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ",
|
7 |
-
"__init__": "<function ActorCriticPolicy.__init__ at
|
8 |
-
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at
|
9 |
-
"reset_noise": "<function ActorCriticPolicy.reset_noise at
|
10 |
-
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at
|
11 |
-
"_build": "<function ActorCriticPolicy._build at
|
12 |
-
"forward": "<function ActorCriticPolicy.forward at
|
13 |
-
"extract_features": "<function ActorCriticPolicy.extract_features at
|
14 |
-
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at
|
15 |
-
"_predict": "<function ActorCriticPolicy._predict at
|
16 |
-
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at
|
17 |
-
"get_distribution": "<function ActorCriticPolicy.get_distribution at
|
18 |
-
"predict_values": "<function ActorCriticPolicy.predict_values at
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
-
"_abc_impl": "<_abc._abc_data object at
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
24 |
-
"observation_space": {
|
25 |
-
":type:": "<class 'gym.spaces.box.Box'>",
|
26 |
-
":serialized:": "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",
|
27 |
-
"dtype": "float32",
|
28 |
-
"_shape": [
|
29 |
-
8
|
30 |
-
],
|
31 |
-
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
32 |
-
"high": "[inf inf inf inf inf inf inf inf]",
|
33 |
-
"bounded_below": "[False False False False False False False False]",
|
34 |
-
"bounded_above": "[False False False False False False False False]",
|
35 |
-
"_np_random": null
|
36 |
-
},
|
37 |
-
"action_space": {
|
38 |
-
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
39 |
-
":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
40 |
-
"n": 4,
|
41 |
-
"_shape": [],
|
42 |
-
"dtype": "int64",
|
43 |
-
"_np_random": null
|
44 |
-
},
|
45 |
-
"n_envs": 16,
|
46 |
"num_timesteps": 16384,
|
47 |
"_total_timesteps": 1000,
|
48 |
"_num_timesteps_at_start": 0,
|
49 |
"seed": null,
|
50 |
"action_noise": null,
|
51 |
-
"start_time":
|
52 |
"learning_rate": 0.0003,
|
53 |
"tensorboard_log": null,
|
54 |
-
"lr_schedule": {
|
55 |
-
":type:": "<class 'function'>",
|
56 |
-
":serialized:": "gAWVwwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOS9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4JDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOS9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/M6kqMFUyYYWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="
|
57 |
-
},
|
58 |
"_last_obs": {
|
59 |
":type:": "<class 'numpy.ndarray'>",
|
60 |
-
":serialized:": "
|
61 |
},
|
62 |
"_last_episode_starts": {
|
63 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -68,15 +42,41 @@
|
|
68 |
"use_sde": false,
|
69 |
"sde_sample_freq": -1,
|
70 |
"_current_progress_remaining": -15.384,
|
|
|
71 |
"ep_info_buffer": {
|
72 |
":type:": "<class 'collections.deque'>",
|
73 |
-
":serialized:": "
|
74 |
},
|
75 |
"ep_success_buffer": {
|
76 |
":type:": "<class 'collections.deque'>",
|
77 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
78 |
},
|
79 |
-
"_n_updates":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
80 |
"n_steps": 1024,
|
81 |
"gamma": 0.999,
|
82 |
"gae_lambda": 0.98,
|
@@ -87,9 +87,13 @@
|
|
87 |
"n_epochs": 4,
|
88 |
"clip_range": {
|
89 |
":type:": "<class 'function'>",
|
90 |
-
":serialized:": "
|
91 |
},
|
92 |
"clip_range_vf": null,
|
93 |
"normalize_advantage": true,
|
94 |
-
"target_kl": null
|
|
|
|
|
|
|
|
|
95 |
}
|
|
|
4 |
":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
5 |
"__module__": "stable_baselines3.common.policies",
|
6 |
"__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ",
|
7 |
+
"__init__": "<function ActorCriticPolicy.__init__ at 0x7f5bc9451750>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f5bc94517e0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f5bc9451870>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f5bc9451900>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f5bc9451990>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f5bc9451a20>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f5bc9451ab0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f5bc9451b40>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f5bc9451bd0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f5bc9451c60>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f5bc9451cf0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f5bc9451d80>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f5bc945c340>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
"num_timesteps": 16384,
|
25 |
"_total_timesteps": 1000,
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
+
"start_time": 1683116033505747256,
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
|
|
|
|
|
|
|
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
+
":serialized:": "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"
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
42 |
"use_sde": false,
|
43 |
"sde_sample_freq": -1,
|
44 |
"_current_progress_remaining": -15.384,
|
45 |
+
"_stats_window_size": 100,
|
46 |
"ep_info_buffer": {
|
47 |
":type:": "<class 'collections.deque'>",
|
48 |
+
":serialized:": "gAWV4AsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHwF91k+X7cfyMAWyUS1+MAXSUR0A5qhBZ6lchdX2UKGgGR8B23hbzK9wnaAdLimgIR0A5q2+fywwCdX2UKGgGR8BtLFOdoWYXaAdLS2gIR0A5vi/wiJO4dX2UKGgGR8Bk7BkCmuTzaAdLYGgIR0A5vmPYFqzrdX2UKGgGR8BV6dUsFt9AaAdLgWgIR0A5wXIU8FINdX2UKGgGR8BkMmOEM9bHaAdLV2gIR0A5wUC7sfJWdX2UKGgGR8BaQiJbdJrdaAdLaWgIR0A5yI8hcJMQdX2UKGgGR8Bq/bV2A5JcaAdLcmgIR0A51oRqXWvsdX2UKGgGR8Bvxyo86mwaaAdLa2gIR0A53WTot+TedX2UKGgGR8B5MCqioKlYaAdLcWgIR0A57SpR4yGjdX2UKGgGR8B9UP9BKL88aAdLbGgIR0A57qz7di2EdX2UKGgGR8B0aryOJcgRaAdLRWgIR0A57sYEW69TdX2UKGgGR8BNydCVrylOaAdLQ2gIR0A58bXHzYmLdX2UKGgGR8BYfGgnMMZxaAdLO2gIR0A5+qmj0tiAdX2UKGgGR8BxoKCcwxnGaAdLYmgIR0A5/0UoKD02dX2UKGgGR8ByYCkFfReDaAdLVWgIR0A6AmJ3xFy8dX2UKGgGR8BbD18kUsWgaAdLaWgIR0A6Ckxh2GIsdX2UKGgGR8BaPdXHR1HOaAdLRmgIR0A6CaPS2H+IdX2UKGgGR8BeXkI5YHPeaAdLRWgIR0A6EAc1fmcOdX2UKGgGR8BxzHNY8uBdaAdLcWgIR0A6Fz1bqyGBdX2UKGgGR8BoMmT9sJpnaAdLZmgIR0A6KBZZB9kSdX2UKGgGR8BU1wokRjBmaAdLS2gIR0A6LD0lJHy3dX2UKGgGR8BpFpNRFZxJaAdLVGgIR0A6Ls54nndPdX2UKGgGR8BiGORJVbRnaAdLQWgIR0A6NbI91U2ldX2UKGgGR8BYVsGcFyJbaAdLUWgIR0A6RJ7LMcIadX2UKGgGR8BjsO6bvw3HaAdLTmgIR0A6Qkj5bhWHdX2UKGgGR8Barc4ku6EraAdLlWgIR0A6RzCDVYp2dX2UKGgGR8BlgQZ88cMmaAdLh2gIR0A6T7GvOhTPdX2UKGgGR8BU4zmr8zhxaAdLUmgIR0A6Wfr8iwB6dX2UKGgGR8Br3v95yEL6aAdLaGgIR0A6abwBo24vdX2UKGgGR8BUN/WtlqagaAdLRWgIR0A6csw+MZP3dX2UKGgGR8Bg5/SKFZgYaAdLX2gIR0A6dbOeJ53UdX2UKGgGR8BannTRYzSDaAdLZmgIR0A6dmnO0LMLdX2UKGgGR8BPzAIppeu3aAdLTGgIR0A6f+OOsDGMdX2UKGgGR8BwK422oegdaAdLaGgIR0A6hauwHJLedX2UKGgGR8BYgMRlHz6KaAdLQWgIR0A6hX+ERJ2/dX2UKGgGR8Bb0ycG1QZXaAdLSGgIR0A6kNWU8mrsdX2UKGgGR8BXqbGBFuvVaAdLYmgIR0A6k4x1xKg7dX2UKGgGR8BR7tWIXTEzaAdLimgIR0A6kRpUPxx2dX2UKGgGR8BnBaQzUI9laAdLh2gIR0A6mGBFuvU0dX2UKGgGR8A9lFXq7iAEaAdLSmgIR0A6m2CNCJGfdX2UKGgGR8BuVoH3UQTVaAdLrGgIR0A6oKtxMnJDdX2UKGgGR8BkIM4rBj4IaAdLeWgIR0A6tE3sHB1tdX2UKGgGR8BsoZOi35N5aAdLfGgIR0A6xHTI/7iydX2UKGgGR8BgR9mrbQC0aAdLPGgIR0A6wssg+yJLdX2UKGgGR8BimNvl2eQNaAdLW2gIR0A6xs+FDfFadX2UKGgGR8Bek0wJw84haAdLUmgIR0A6yTURWcSXdX2UKGgGR8BpBex8lXzUaAdLRWgIR0A618+A3DNydX2UKGgGR8BiQeGh24d7aAdLQWgIR0A624AS39aVdX2UKGgGR8BfRenVG0/oaAdLZGgIR0A62/bCaZx8dX2UKGgGR8BE/wzk6tDEaAdLQmgIR0A64AeJYT0ydX2UKGgGR8BuveS0Sh8IaAdLg2gIR0A64cBU70WedX2UKGgGR8BguRiy6cy4aAdLYGgIR0A64qgAZKnOdX2UKGgGR8BWrM01qFh5aAdLQmgIR0A65ftx+8XfdX2UKGgGR8BzdTGbTc7AaAdLWmgIR0A67M7EHdGidX2UKGgGR8BkzoUi6g/UaAdLfGgIR0A68Ij4YaYNdX2UKGgGR8BWwUBGQSzxaAdLbWgIR0A684Ju2qkudX2UKGgGR8B8HfGrCFbnaAdLZmgIR0A6+gfEGZ/kdX2UKGgGR8Bn1wiHIp6QaAdLQGgIR0A7CMQEpy6udX2UKGgGR8BOmrn9vS+haAdLOGgIR0A7EoF3Y+SsdX2UKGgGR8BQ+n+l0o0AaAdLQ2gIR0A7GcfvF3pwdX2UKGgGR8BA7ITGo73gaAdLeGgIR0A7LIcinpB5dX2UKGgGR8BZAsIZ62ORaAdLTGgIR0A7PGrS3LFGdX2UKGgGR8BaT2ATZg5SaAdLeWgIR0A7PGd7OVxCdX2UKGgGR8BdesBltj0+aAdLXWgIR0A7PGACnxaxdX2UKGgGR8B2bh67dznzaAdLXmgIR0A7PxREWqLkdX2UKGgGR8B3CInc+JP7aAdLS2gIR0A7P7aZhKDkdX2UKGgGR8Bw7/+ERJ2/aAdLSGgIR0A7Q+Sr5qM4dX2UKGgGR8Bob5u0kWykaAdLa2gIR0A7R3b212JSdX2UKGgGR8BZGrJnxri3aAdLZWgIR0A7TCkoF3Y+dX2UKGgGR8Bx6YhfShJzaAdLjGgIR0A7VKHwgDA8dX2UKGgGR8Bq4nr2QGOdaAdLZGgIR0A7VbrC3w1BdX2UKGgGR8BdZXN9ph4MaAdLkWgIR0A7Xf+jua4MdX2UKGgGR8Ba6piy6cy4aAdLd2gIR0A7XhcqvvBrdX2UKGgGR8BdZiprDZUUaAdLUmgIR0A7caLn9vS/dX2UKGgGR8BuXAOFxn3+aAdLWWgIR0A7cWcz67/XdX2UKGgGR8BXzylabF0gaAdLQ2gIR0A7dOsT37DVdX2UKGgGR8BWRe0PYnOTaAdLQ2gIR0A7g1uivgWKdX2UKGgGR8Bdl/2K2rn1aAdLQGgIR0A7iczZYgaFdX2UKGgGR8BQk8YIjW07aAdLRmgIR0A7jPdVNpM6dX2UKGgGR8BW3APNFBppaAdLVWgIR0A7lMLncL0BdX2UKGgGR8BzIBQKrq+raAdLlWgIR0A7pCiyprDZdX2UKGgGR8B9sGdwvQF+aAdLYWgIR0A7pZ4fOlfrdX2UKGgGR8BWGKgZjx0/aAdLZ2gIR0A7q7mMfigkdX2UKGgGR8BqG/sgMc6vaAdLaWgIR0A7q3b212JSdX2UKGgGR8BgdnseGO+7aAdLV2gIR0A7rmIj4YaYdX2UKGgGR8Bbex2B8QZoaAdLT2gIR0A7rctoSL62dX2UKGgGR8BdSWwFC9h7aAdLU2gIR0A7sbSqlxffdX2UKGgGR8BuFzHbRF7VaAdLaGgIR0A7t6tknTiLdX2UKGgGR8BjNB7HAAQyaAdLYWgIR0A7t14Pf8/EdX2UKGgGR8BaawcDKYAsaAdLUGgIR0A7wXNTtLL7dX2UKGgGR8Bwvxr0rbxmaAdLVWgIR0A7yUahpQDWdX2UKGgGR8BxPof/3nIRaAdLZGgIR0A71K6FuejEdX2UKGgGR8Bi2BaA4GUwaAdLSGgIR0A73RfnfVI7dX2UKGgGR8BbqoSlFc6eaAdLYWgIR0A75HLidat+dX2UKGgGR8BeQKYJE6T4aAdLWmgIR0A751schkiEdX2UKGgGR8BNKrVnVXmvaAdLPWgIR0A76XKbKA8TdX2UKGgGR8BpguuA7PpqaAdLQmgIR0A75pSaVlf7dX2UKGgGR8Bhx170Fr2yaAdLYmgIR0A77G0eEIw/dX2UKGgGR8BT/2UnogV5aAdLRGgIR0A77inpB5X2dWUu"
|
49 |
},
|
50 |
"ep_success_buffer": {
|
51 |
":type:": "<class 'collections.deque'>",
|
52 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
},
|
54 |
+
"_n_updates": 5,
|
55 |
+
"observation_space": {
|
56 |
+
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
+
":serialized:": "gAWVcAIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoECiWCAAAAAAAAAABAQEBAQEBAZRoFEsIhZRoGHSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBAoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaApLCIWUaBh0lFKUjARoaWdolGgQKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgKSwiFlGgYdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=",
|
58 |
+
"dtype": "float32",
|
59 |
+
"bounded_below": "[ True True True True True True True True]",
|
60 |
+
"bounded_above": "[ True True True True True True True True]",
|
61 |
+
"_shape": [
|
62 |
+
8
|
63 |
+
],
|
64 |
+
"low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
|
65 |
+
"high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
|
66 |
+
"low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
|
67 |
+
"high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
|
68 |
+
"_np_random": null
|
69 |
+
},
|
70 |
+
"action_space": {
|
71 |
+
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
72 |
+
":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=",
|
73 |
+
"n": "4",
|
74 |
+
"start": "0",
|
75 |
+
"_shape": [],
|
76 |
+
"dtype": "int64",
|
77 |
+
"_np_random": null
|
78 |
+
},
|
79 |
+
"n_envs": 16,
|
80 |
"n_steps": 1024,
|
81 |
"gamma": 0.999,
|
82 |
"gae_lambda": 0.98,
|
|
|
87 |
"n_epochs": 4,
|
88 |
"clip_range": {
|
89 |
":type:": "<class 'function'>",
|
90 |
+
":serialized:": "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"
|
91 |
},
|
92 |
"clip_range_vf": null,
|
93 |
"normalize_advantage": true,
|
94 |
+
"target_kl": null,
|
95 |
+
"lr_schedule": {
|
96 |
+
":type:": "<class 'function'>",
|
97 |
+
":serialized:": "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"
|
98 |
+
}
|
99 |
}
|
ppo-LunarLander-v2/policy.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 87929
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f89ee1498fcf7bac7b237814638a278c45188ee3feda86169cf456cd4eacff4a
|
3 |
size 87929
|
ppo-LunarLander-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbd6669485512fcd635731d6f6e5746cc22587ec94ff48ece282c3358d17b477
|
3 |
+
size 43329
|
ppo-LunarLander-v2/system_info.txt
CHANGED
@@ -1,7 +1,9 @@
|
|
1 |
- OS: Linux-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
|
2 |
-
- Python: 3.
|
3 |
-
- Stable-Baselines3:
|
4 |
-
- PyTorch:
|
5 |
- GPU Enabled: True
|
6 |
- Numpy: 1.22.4
|
7 |
-
-
|
|
|
|
|
|
1 |
- OS: Linux-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
|
2 |
+
- Python: 3.10.11
|
3 |
+
- Stable-Baselines3: 2.0.0a5
|
4 |
+
- PyTorch: 2.0.0+cu118
|
5 |
- GPU Enabled: True
|
6 |
- Numpy: 1.22.4
|
7 |
+
- Cloudpickle: 2.2.1
|
8 |
+
- Gymnasium: 0.28.1
|
9 |
+
- OpenAI Gym: 0.25.2
|
replay.mp4
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7723eab4bdb82a38012a4d8893f6672f9963b3d4a55d3294c4d49f263b5f75db
|
3 |
+
size 168471
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward": -
|
|
|
1 |
+
{"mean_reward": -176.7370768138673, "std_reward": 83.90166135676407, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-05-03T12:14:34.487696"}
|