javiervela
commited on
Commit
•
1f2d328
1
Parent(s):
09fcdcc
Upload PPO LunarLander-v2 trained agent
Browse files- README.md +16 -40
- config.json +1 -1
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/_stable_baselines3_version +1 -1
- ppo-LunarLander-v2/data +19 -18
- ppo-LunarLander-v2/policy.optimizer.pth +1 -1
- ppo-LunarLander-v2/policy.pth +2 -2
- ppo-LunarLander-v2/system_info.txt +7 -7
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
@@ -1,11 +1,10 @@
|
|
1 |
---
|
|
|
2 |
tags:
|
3 |
- LunarLander-v2
|
4 |
-
- ppo
|
5 |
- deep-reinforcement-learning
|
6 |
- reinforcement-learning
|
7 |
-
-
|
8 |
-
- deep-rl-course
|
9 |
model-index:
|
10 |
- name: PPO
|
11 |
results:
|
@@ -17,45 +16,22 @@ model-index:
|
|
17 |
type: LunarLander-v2
|
18 |
metrics:
|
19 |
- type: mean_reward
|
20 |
-
value:
|
21 |
name: mean_reward
|
22 |
verified: false
|
23 |
---
|
24 |
|
25 |
-
|
|
|
|
|
26 |
|
27 |
-
|
28 |
-
|
29 |
-
|
30 |
-
|
31 |
-
|
32 |
-
|
33 |
-
|
34 |
-
|
35 |
-
|
36 |
-
|
37 |
-
'wandb_entity': None
|
38 |
-
'capture_video': False
|
39 |
-
'env_id': 'LunarLander-v2'
|
40 |
-
'total_timesteps': 50000
|
41 |
-
'learning_rate': 0.00025
|
42 |
-
'num_envs': 4
|
43 |
-
'num_steps': 128
|
44 |
-
'anneal_lr': True
|
45 |
-
'gae': True
|
46 |
-
'gamma': 0.99
|
47 |
-
'gae_lambda': 0.95
|
48 |
-
'num_minibatches': 4
|
49 |
-
'update_epochs': 4
|
50 |
-
'norm_adv': True
|
51 |
-
'clip_coef': 0.2
|
52 |
-
'clip_vloss': True
|
53 |
-
'ent_coef': 0.01
|
54 |
-
'vf_coef': 0.5
|
55 |
-
'max_grad_norm': 0.5
|
56 |
-
'target_kl': None
|
57 |
-
'repo_id': 'javiervela/ppo-LunarLander-v2'
|
58 |
-
'batch_size': 512
|
59 |
-
'minibatch_size': 128}
|
60 |
-
```
|
61 |
-
|
|
|
1 |
---
|
2 |
+
library_name: stable-baselines3
|
3 |
tags:
|
4 |
- LunarLander-v2
|
|
|
5 |
- deep-reinforcement-learning
|
6 |
- reinforcement-learning
|
7 |
+
- stable-baselines3
|
|
|
8 |
model-index:
|
9 |
- name: PPO
|
10 |
results:
|
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: 264.38 +/- 14.94
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
23 |
|
24 |
+
# **PPO** Agent playing **LunarLander-v2**
|
25 |
+
This is a trained model of a **PPO** agent playing **LunarLander-v2**
|
26 |
+
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
27 |
|
28 |
+
## Usage (with Stable-baselines3)
|
29 |
+
TODO: Add your code
|
30 |
+
|
31 |
+
|
32 |
+
```python
|
33 |
+
from stable_baselines3 import ...
|
34 |
+
from huggingface_sb3 import load_from_hub
|
35 |
+
|
36 |
+
...
|
37 |
+
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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 0x7f36bb0a65e0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f36bb0a6670>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f36bb0a6700>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f36bb0a6790>", "_build": "<function ActorCriticPolicy._build at 0x7f36bb0a6820>", "forward": "<function ActorCriticPolicy.forward at 0x7f36bb0a68b0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f36bb0a6940>", "_predict": "<function ActorCriticPolicy._predict at 0x7f36bb0a69d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f36bb0a6a60>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f36bb0a6af0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f36bb0a6b80>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f36bb09de10>"}, "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": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1670753320142098431, "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": -0.015808000000000044, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 248, "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, "system_info": {"OS": "Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu116", "GPU Enabled": "True", "Numpy": "1.21.6", "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 0x7ff9d26f91f0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff9d26f9280>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff9d26f9310>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff9d26f93a0>", "_build": "<function ActorCriticPolicy._build at 0x7ff9d26f9430>", "forward": "<function ActorCriticPolicy.forward at 0x7ff9d26f94c0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ff9d26f9550>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff9d26f95e0>", "_predict": "<function ActorCriticPolicy._predict at 0x7ff9d26f9670>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff9d26f9700>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff9d26f9790>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff9d26f9820>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7ff9d26f5810>"}, "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": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1677838678994379151, "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": -0.015808000000000044, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 248, "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, "system_info": {"OS": "Linux-5.10.147+-x86_64-with-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.8.10", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu116", "GPU Enabled": "True", "Numpy": "1.22.4", "Gym": "0.21.0"}}
|
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:a84a2a7a62f4d262be44e82cbf651dfa63db0eadc7e8674788d6cc20f8b8143c
|
3 |
+
size 147416
|
ppo-LunarLander-v2/_stable_baselines3_version
CHANGED
@@ -1 +1 @@
|
|
1 |
-
1.
|
|
|
1 |
+
1.7.0
|
ppo-LunarLander-v2/data
CHANGED
@@ -3,20 +3,21 @@
|
|
3 |
":type:": "<class 'abc.ABCMeta'>",
|
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
|
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 |
-
"
|
14 |
-
"
|
15 |
-
"
|
16 |
-
"
|
17 |
-
"
|
|
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
-
"_abc_impl": "<_abc_data object at
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
@@ -47,16 +48,16 @@
|
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
-
"start_time":
|
51 |
"learning_rate": 0.0003,
|
52 |
"tensorboard_log": null,
|
53 |
"lr_schedule": {
|
54 |
":type:": "<class 'function'>",
|
55 |
-
":serialized:": "gAWVwwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+
|
56 |
},
|
57 |
"_last_obs": {
|
58 |
":type:": "<class 'numpy.ndarray'>",
|
59 |
-
":serialized:": "
|
60 |
},
|
61 |
"_last_episode_starts": {
|
62 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -69,7 +70,7 @@
|
|
69 |
"_current_progress_remaining": -0.015808000000000044,
|
70 |
"ep_info_buffer": {
|
71 |
":type:": "<class 'collections.deque'>",
|
72 |
-
":serialized:": "
|
73 |
},
|
74 |
"ep_success_buffer": {
|
75 |
":type:": "<class 'collections.deque'>",
|
@@ -86,7 +87,7 @@
|
|
86 |
"n_epochs": 4,
|
87 |
"clip_range": {
|
88 |
":type:": "<class 'function'>",
|
89 |
-
":serialized:": "gAWVwwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+
|
90 |
},
|
91 |
"clip_range_vf": null,
|
92 |
"normalize_advantage": true,
|
|
|
3 |
":type:": "<class 'abc.ABCMeta'>",
|
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 0x7ff9d26f91f0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff9d26f9280>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff9d26f9310>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff9d26f93a0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7ff9d26f9430>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7ff9d26f94c0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7ff9d26f9550>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff9d26f95e0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7ff9d26f9670>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff9d26f9700>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff9d26f9790>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff9d26f9820>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc_data object at 0x7ff9d26f5810>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
|
|
48 |
"_num_timesteps_at_start": 0,
|
49 |
"seed": null,
|
50 |
"action_noise": null,
|
51 |
+
"start_time": 1677838678994379151,
|
52 |
"learning_rate": 0.0003,
|
53 |
"tensorboard_log": null,
|
54 |
"lr_schedule": {
|
55 |
":type:": "<class 'function'>",
|
56 |
+
":serialized:": "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"
|
57 |
},
|
58 |
"_last_obs": {
|
59 |
":type:": "<class 'numpy.ndarray'>",
|
60 |
+
":serialized:": "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"
|
61 |
},
|
62 |
"_last_episode_starts": {
|
63 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
70 |
"_current_progress_remaining": -0.015808000000000044,
|
71 |
"ep_info_buffer": {
|
72 |
":type:": "<class 'collections.deque'>",
|
73 |
+
":serialized:": "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"
|
74 |
},
|
75 |
"ep_success_buffer": {
|
76 |
":type:": "<class 'collections.deque'>",
|
|
|
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,
|
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 sha256:42a4763043c18cd86f6c7bfb2c522cb6261e25f0960161310d12e7eeb55159b1
|
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:b28c0d2ecfaaea1f56e1cc2a1cdb6f8fa860ff07d8308da8474e61d866d95ddb
|
3 |
+
size 43393
|
ppo-LunarLander-v2/system_info.txt
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
-
OS: Linux-5.10.
|
2 |
-
Python: 3.8.
|
3 |
-
Stable-Baselines3: 1.
|
4 |
-
PyTorch: 1.13.
|
5 |
-
GPU Enabled: True
|
6 |
-
Numpy: 1.
|
7 |
-
Gym: 0.21.0
|
|
|
1 |
+
- OS: Linux-5.10.147+-x86_64-with-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
|
2 |
+
- Python: 3.8.10
|
3 |
+
- Stable-Baselines3: 1.7.0
|
4 |
+
- PyTorch: 1.13.1+cu116
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.22.4
|
7 |
+
- Gym: 0.21.0
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"
|
|
|
1 |
+
{"mean_reward": 264.3823912999123, "std_reward": 14.937792489321629, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-03T10:41:44.239654"}
|