Unit1

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -525.44 +/- 120.14
+      value: 275.63 +/- 17.23
       name: mean_reward
       verified: false
 ---

config.json

@@ -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 0x79d709a193a0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x79d709a19440>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x79d709a194e0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x79d709a19580>", "_build": "<function ActorCriticPolicy._build at 0x79d709a19620>", "forward": "<function ActorCriticPolicy.forward at 0x79d709a196c0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x79d709a19760>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x79d709a19800>", "_predict": "<function ActorCriticPolicy._predict at 0x79d709a198a0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x79d709a19940>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x79d709a199e0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x79d709a19a80>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x79d709b0b900>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 8016, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1750621230423648761, "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:": "gAWVhAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 1.0, "_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": 0, "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:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZROdWIu", "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:": "gAWV1gIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwiVAZcAiQFTAJROhZQpjAFflIWUjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjExL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUS4RDCPiAANgPEogKlEMAlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTEvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpRoAIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCF9lH2UKGgYjARmdW5jlIwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBmMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHP8mZmZmZmZqFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.123+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Mar 30 16:01:29 UTC 2025", "Python": "3.11.13", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.6.0+cu124", "GPU Enabled": "False", "Numpy": "2.0.2", "Cloudpickle": "3.1.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
+{"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 0x7d82dc81af20>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d82dc81afc0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d82dc81b060>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d82dc81b100>", "_build": "<function ActorCriticPolicy._build at 0x7d82dc81b1a0>", "forward": "<function ActorCriticPolicy.forward at 0x7d82dc81b240>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d82dc81b2e0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d82dc81b380>", "_predict": "<function ActorCriticPolicy._predict at 0x7d82dc81b420>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d82dc81b4c0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d82dc81b560>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d82dc81b600>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7d82dc975ec0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 2015232, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1750772661900054908, "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:": "gAWVhAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.007616000000000067, "_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": 738, "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:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 1024, "gamma": 0.99, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 6, "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-6.1.123+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Mar 30 16:01:29 UTC 2025", "Python": "3.11.13", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.6.0+cu124", "GPU Enabled": "True", "Numpy": "2.0.2", "Cloudpickle": "3.1.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfe58bc634a7f26dd724bfba2a07092c5b1216e0065cb4a8d9bd898884a8b105
-size 59808
+oid sha256:c21a1d34fe1d0d7e153fdc00438ae3ed724f18f95f4bc69ce135fde107307a08
+size 148011

ppo-LunarLander-v2/data

@@ -4,34 +4,34 @@
         ":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 0x79d709a193a0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x79d709a19440>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x79d709a194e0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x79d709a19580>",
-        "_build": "<function ActorCriticPolicy._build at 0x79d709a19620>",
-        "forward": "<function ActorCriticPolicy.forward at 0x79d709a196c0>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x79d709a19760>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x79d709a19800>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x79d709a198a0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x79d709a19940>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x79d709a199e0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x79d709a19a80>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7d82dc81af20>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d82dc81afc0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d82dc81b060>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d82dc81b100>",
+        "_build": "<function ActorCriticPolicy._build at 0x7d82dc81b1a0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7d82dc81b240>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d82dc81b2e0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d82dc81b380>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7d82dc81b420>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d82dc81b4c0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d82dc81b560>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d82dc81b600>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x79d709b0b900>"
+        "_abc_impl": "<_abc._abc_data object at 0x7d82dc975ec0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 8016,
-    "_total_timesteps": 1000000,
+    "num_timesteps": 2015232,
+    "_total_timesteps": 2000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1750621230423648761,
+    "start_time": 1750772661900054908,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -41,17 +41,17 @@
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": 1.0,
+    "_current_progress_remaining": -0.007616000000000067,
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 0,
+    "_n_updates": 738,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -78,13 +78,13 @@
     },
     "n_envs": 16,
     "n_steps": 1024,
-    "gamma": 0.999,
+    "gamma": 0.99,
     "gae_lambda": 0.98,
     "ent_coef": 0.01,
     "vf_coef": 0.5,
     "max_grad_norm": 0.5,
     "batch_size": 64,
-    "n_epochs": 4,
+    "n_epochs": 6,
     "clip_range": {
         ":type:": "<class 'function'>",
         ":serialized:": "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"

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13dbf41e305d3a0b52e13b973ece0bb28ffca5bcf57636bcf9b68102feec544e
-size 1120
+oid sha256:9ae3d8c3d1bb7b8c977495c9074abc1d3491fd65faabef64b3896e3eda1fd85d
+size 88362

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e1414487988e92c76d3e9f65a48fb6ec26c69c4634a4d6331f3ad2f77c72c15
-size 43634
+oid sha256:023c3c8f1b1465b0467bfce6c37171fef883a9885d3cb887fdc50ec37a56d633
+size 43762

ppo-LunarLander-v2/system_info.txt

@@ -2,7 +2,7 @@
 - Python: 3.11.13
 - Stable-Baselines3: 2.0.0a5
 - PyTorch: 2.6.0+cu124
-- GPU Enabled: False
+- GPU Enabled: True
 - Numpy: 2.0.2
 - Cloudpickle: 3.1.1
 - Gymnasium: 0.28.1

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4930265fcebcc4acfcd58ac1e29281fb7aa2875861fc4e6a271b4af3f81d5f57
-size 210822
+oid sha256:54ce6e759d84fc7863d3dbfe43b70f86a1a79803388387dba0ed3efb70504af2
+size 144553

results.json

@@ -1 +1 @@
-{"mean_reward": -525.436169583723, "std_reward": 120.14438390315159, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-06-22T19:54:33.836453"}
+{"mean_reward": 275.62705539999996, "std_reward": 17.233989063071242, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-06-24T14:28:24.948169"}