First commit

PPO-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6ccd17f5469e06e7e01d9dff0e432249fed5b8e2a326638cbbee6735067f62e
-size 147330
+oid sha256:1a9cb36ef00e88716683a7e903c93dee6e20a57efaa37bdaef0d9422976e8284
+size 147211

PPO-LunarLander-v2/data

@@ -4,20 +4,20 @@
         ":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 0x7b72181b0040>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b72181b00d0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b72181b0160>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b72181b01f0>",
-        "_build": "<function ActorCriticPolicy._build at 0x7b72181b0280>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7b72181b0310>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b72181b03a0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b72181b0430>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7b72181b04c0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b72181b0550>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b72181b05e0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b72181b0670>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7d66bc30dab0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d66bc30db40>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d66bc30dbd0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d66bc30dc60>",
+        "_build": "<function ActorCriticPolicy._build at 0x7d66bc30dcf0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7d66bc30dd80>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d66bc30de10>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d66bc30dea0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7d66bc30df30>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d66bc30dfc0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d66bc30e050>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d66bc30e0e0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7b72181af6c0>"
+        "_abc_impl": "<_abc._abc_data object at 0x7d66bc319140>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -29,10 +29,7 @@
     "start_time": 1730354831494534567,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
-    "_last_obs": {
-        ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAHpjCj7T7YY+IaWOvXK9Vr4gcRY8yqAEPQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
-    },
+    "_last_obs": null,
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
         ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
@@ -69,7 +66,7 @@
     },
     "action_space": {
         ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
-        ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
+        ":serialized:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
         "n": "4",
         "start": "0",
         "_shape": [],

PPO-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00aa7774a9e6fe30d8d0ca55eb10d3b59487d07061e24e5e17e66175418f6e90
-size 88362
+oid sha256:504e713d37f8245292ec38de6c05a26880baa0bc9a4f653e7fa8e9ebf8733ca8
+size 88490

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 247.05 +/- 15.77
+      value: 271.48 +/- 16.91
       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 0x7b72181b0040>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b72181b00d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b72181b0160>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b72181b01f0>", "_build": "<function ActorCriticPolicy._build at 0x7b72181b0280>", "forward": "<function ActorCriticPolicy.forward at 0x7b72181b0310>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b72181b03a0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b72181b0430>", "_predict": "<function ActorCriticPolicy._predict at 0x7b72181b04c0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b72181b0550>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b72181b05e0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b72181b0670>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7b72181af6c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1000448, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1730354831494534567, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAHpjCj7T7YY+IaWOvXK9Vr4gcRY8yqAEPQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.00044800000000000395, "_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": 3908, "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": 1, "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-5.15.154+-x86_64-with-glibc2.35 # 1 SMP Thu Jun 27 20:43:36 UTC 2024", "Python": "3.10.14", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.4.0", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.0.0", "Gymnasium": "0.28.1", "OpenAI Gym": "0.26.2"}}
+{"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 0x7d66bc30dab0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d66bc30db40>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d66bc30dbd0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d66bc30dc60>", "_build": "<function ActorCriticPolicy._build at 0x7d66bc30dcf0>", "forward": "<function ActorCriticPolicy.forward at 0x7d66bc30dd80>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d66bc30de10>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d66bc30dea0>", "_predict": "<function ActorCriticPolicy._predict at 0x7d66bc30df30>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d66bc30dfc0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d66bc30e050>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d66bc30e0e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7d66bc319140>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1000448, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1730354831494534567, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": null, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.00044800000000000395, "_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": 3908, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "gAWVdgIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoCIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoESiWCAAAAAAAAAABAQEBAQEBAZRoFUsIhZRoGXSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBEoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaAtLCIWUaBl0lFKUjARoaWdolGgRKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgLSwiFlGgZdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=", "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": 1, "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:": "gAWVqAIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS9vcHQvY29uZGEvbGliL3B5dGhvbjMuMTAvc2l0ZS1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvb3B0L2NvbmRhL2xpYi9weXRob24zLjEwL3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUaACMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/M6kqMFUyYYWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "system_info": {"OS": "Linux-5.15.154+-x86_64-with-glibc2.35 # 1 SMP Thu Jun 27 20:43:36 UTC 2024", "Python": "3.10.14", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.4.0", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.0.0", "Gymnasium": "0.28.1", "OpenAI Gym": "0.26.2"}}

results.json

@@ -1 +1 @@
-{"mean_reward": 247.0533308285322, "std_reward": 15.77323885848392, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-10-31T07:47:28.791723"}
+{"mean_reward": 271.47513768752674, "std_reward": 16.911159722370048, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-10-31T07:58:33.962683"}