My second RL training attempt!

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 288.58 +/- 17.50
+      value: -562.58 +/- 93.94
       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 0x79e1c66343a0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x79e1c6634430>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x79e1c66344c0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x79e1c6634550>", "_build": "<function ActorCriticPolicy._build at 0x79e1c66345e0>", "forward": "<function ActorCriticPolicy.forward at 0x79e1c6634670>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x79e1c6634700>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x79e1c6634790>", "_predict": "<function ActorCriticPolicy._predict at 0x79e1c6634820>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x79e1c66348b0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x79e1c6634940>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x79e1c66349d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x79e1c65d4980>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 2015232, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1723277108092078569, "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:": "gAWViwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYYAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLGIWUjAFDlHSUUpQu"}, "_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": 618, "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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 24, "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": 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-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.3.1+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "2.2.1", "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 0x7d0716d4a4d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d0716d4a560>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d0716d4a5f0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d0716d4a680>", "_build": "<function ActorCriticPolicy._build at 0x7d0716d4a710>", "forward": "<function ActorCriticPolicy.forward at 0x7d0716d4a7a0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d0716d4a830>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d0716d4a8c0>", "_predict": "<function ActorCriticPolicy._predict at 0x7d0716d4a950>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d0716d4a9e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d0716d4aa70>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d0716d4ab00>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7d0716ce6d40>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "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", "features_extractor_class": "<class '__main__.CustomFeatureExtractor'>", "features_extractor_kwargs": {"features_dim": 64}}, "num_timesteps": 0, "_total_timesteps": 0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 0.0, "learning_rate": 0.0002, "tensorboard_log": null, "_last_obs": null, "_last_episode_starts": null, "_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": null, "ep_success_buffer": null, "_n_updates": 0, "n_steps": 512, "gamma": 0.99999, "gae_lambda": 0.98, "ent_coef": 0.02, "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, "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:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 48, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.3.1+cu121", "GPU Enabled": "False", "Numpy": "1.26.4", "Cloudpickle": "2.2.1", "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 sha256:604dafd5894332f99d0ed754ced378aefb44813332bbbbc716fe738dc16de587
-size 148304
+oid sha256:0147f6eca8d6997e5cd8a22893c06d253c5e9616f503a0dfc33d830bfcc21b63
+size 107482

ppo-LunarLander-v2/data

@@ -4,54 +4,64 @@
         ":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 0x79e1c66343a0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x79e1c6634430>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x79e1c66344c0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x79e1c6634550>",
-        "_build": "<function ActorCriticPolicy._build at 0x79e1c66345e0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x79e1c6634670>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x79e1c6634700>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x79e1c6634790>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x79e1c6634820>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x79e1c66348b0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x79e1c6634940>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x79e1c66349d0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7d0716d4a4d0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d0716d4a560>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d0716d4a5f0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d0716d4a680>",
+        "_build": "<function ActorCriticPolicy._build at 0x7d0716d4a710>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7d0716d4a7a0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d0716d4a830>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d0716d4a8c0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7d0716d4a950>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d0716d4a9e0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d0716d4aa70>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d0716d4ab00>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x79e1c65d4980>"
+        "_abc_impl": "<_abc._abc_data object at 0x7d0716ce6d40>"
     },
     "verbose": 1,
-    "policy_kwargs": {},
-    "num_timesteps": 2015232,
-    "_total_timesteps": 2000000,
+    "policy_kwargs": {
+        ":type:": "<class 'dict'>",
+        ":serialized:": "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",
+        "features_extractor_class": "<class '__main__.CustomFeatureExtractor'>",
+        "features_extractor_kwargs": {
+            "features_dim": 64
+        }
+    },
+    "num_timesteps": 0,
+    "_total_timesteps": 0,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1723277108092078569,
-    "learning_rate": 0.0003,
+    "start_time": 0.0,
+    "learning_rate": 0.0002,
     "tensorboard_log": null,
-    "_last_obs": {
-        ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "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"
-    },
-    "_last_episode_starts": {
-        ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWViwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYYAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLGIWUjAFDlHSUUpQu"
-    },
+    "_last_obs": null,
+    "_last_episode_starts": null,
     "_last_original_obs": null,
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.007616000000000067,
+    "_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=="
+    "ep_info_buffer": null,
+    "ep_success_buffer": null,
+    "_n_updates": 0,
+    "n_steps": 512,
+    "gamma": 0.99999,
+    "gae_lambda": 0.98,
+    "ent_coef": 0.02,
+    "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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"
     },
-    "_n_updates": 618,
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -69,31 +79,16 @@
     },
     "action_space": {
         ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
-        ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
+        ":serialized:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
         "n": "4",
         "start": "0",
         "_shape": [],
         "dtype": "int64",
         "_np_random": null
     },
-    "n_envs": 24,
-    "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": 6,
-    "clip_range": {
-        ":type:": "<class 'function'>",
-        ":serialized:": "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"
-    },
-    "clip_range_vf": null,
-    "normalize_advantage": true,
-    "target_kl": null,
+    "n_envs": 48,
     "lr_schedule": {
         ":type:": "<class 'function'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     }
 }

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7323167b9043e3bf5ebb3144ab6f668f7bc3d85daf2037c9b67e7716a8af0448
-size 88362
+oid sha256:21784c15809704f5cd900386d677c907f154527210f58f46324ba18dbd079ec8
+size 1120

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8351f1469db4d090b9b34ef28823f681751cd6441e3b3216c57522df83e9f587
-size 43762
+oid sha256:9a14a150ab22f5f8fc2a4979aa5b7d0140959bb8ea0e2c7db07c58d3a1a8627b
+size 93414

ppo-LunarLander-v2/system_info.txt

@@ -2,7 +2,7 @@
 - Python: 3.10.12
 - Stable-Baselines3: 2.0.0a5
 - PyTorch: 2.3.1+cu121
-- GPU Enabled: True
+- GPU Enabled: False
 - Numpy: 1.26.4
 - Cloudpickle: 2.2.1
 - Gymnasium: 0.28.1

results.json

@@ -1 +1 @@
-{"mean_reward": 288.58203629999997, "std_reward": 17.50023990088199, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-10T08:41:25.012583"}
+{"mean_reward": -562.5759415, "std_reward": 93.93795511655733, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-11T17:52:49.680421"}