Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 236.63 +/- 66.83
+      value: 255.63 +/- 21.44
       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 0x7c496286cd30>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c496286cdc0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c496286ce50>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c496286cee0>", "_build": "<function ActorCriticPolicy._build at 0x7c496286cf70>", "forward": "<function ActorCriticPolicy.forward at 0x7c496286d000>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c496286d090>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c496286d120>", "_predict": "<function ActorCriticPolicy._predict at 0x7c496286d1b0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c496286d240>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c496286d2d0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c496286d360>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7c4962861b80>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1000448, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1709650193569048890, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAM3abL32gBm6Hr7POF4SYDPygKa7bRP0twAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "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 0x7fce8bfc6170>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fce8bfc6200>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fce8bfc6290>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fce8bfc6320>", "_build": "<function ActorCriticPolicy._build at 0x7fce8bfc63b0>", "forward": "<function ActorCriticPolicy.forward at 0x7fce8bfc6440>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fce8bfc64d0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fce8bfc6560>", "_predict": "<function ActorCriticPolicy._predict at 0x7fce8bfc65f0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fce8bfc6680>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fce8bfc6710>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fce8bfc67a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fce8c163100>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1000448, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1710946352236949255, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAOlq76V0Js/J7rHvvcnyb6GabK+GsYPvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": 15632, "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:": "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": 16, "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-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.1+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "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:de6e763edc991cdf3520c77a2ffbd33a84ca7b2a6606e5675467d694353ff5a2
-size 147402
+oid sha256:4609c57fce2cc4e73ec95d04b5e743a947b48bcf7fb1c03a1435fd26b82b2124
+size 147432

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 0x7c496286cd30>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c496286cdc0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c496286ce50>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c496286cee0>",
-        "_build": "<function ActorCriticPolicy._build at 0x7c496286cf70>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7c496286d000>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c496286d090>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c496286d120>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7c496286d1b0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c496286d240>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c496286d2d0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c496286d360>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7fce8bfc6170>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fce8bfc6200>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fce8bfc6290>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fce8bfc6320>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fce8bfc63b0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fce8bfc6440>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fce8bfc64d0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fce8bfc6560>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fce8bfc65f0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fce8bfc6680>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fce8bfc6710>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fce8bfc67a0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7c4962861b80>"
+        "_abc_impl": "<_abc._abc_data object at 0x7fce8c163100>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -26,12 +26,12 @@
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1709650193569048890,
+    "start_time": 1710946352236949255,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAM3abL32gBm6Hr7POF4SYDPygKa7bRP0twAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAOlq76V0Js/J7rHvvcnyb6GabK+GsYPvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -45,13 +45,13 @@
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "gAWVMAwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHv+UY51eSjg2MAWyUTQoBjAF0lEdAmq6M7hegMHV9lChoBkdAXiUdQwblzWgHTegDaAhHQJq2MXdj5Kx1fZQoaAZHQDdwTbnHNotoB0vfaAhHQJq3v1RLsa91fZQoaAZHwBn+BxxT851oB00EAWgIR0Caucfm9xp+dX2UKGgGR0BtVtk8RtgsaAdNOgFoCEdAmrzUyP+4snV9lChoBkdAbBSsS00FbGgHTR8BaAhHQJq+YRjBl+V1fZQoaAZHQG+ynRkVerxoB00ZAWgIR0Cav+TkyULVdX2UKGgGR0BxV9fTkQwsaAdNyQJoCEdAmsT7rHEMs3V9lChoBkdAbOkNz8xbjmgHTUEBaAhHQJrGtEjPfKp1fZQoaAZHQE40yyD7IktoB0vtaAhHQJrJI3o9s8B1fZQoaAZHQG0gObqhUR5oB01bAWgIR0CayxzND+irdX2UKGgGR0BCIN1IRRMwaAdL9WgIR0CazHLg4wRHdX2UKGgGR0AzMoa1kUblaAdNFwFoCEdAms32pyZKF3V9lChoBkdAbb6gyuZCwGgHTRcBaAhHQJrQn+dbxEx1fZQoaAZHQHBS2uPmxMZoB00vAWgIR0Ca0lRlYlpodX2UKGgGR0BxZfeHi3ocaAdNugFoCEdAmtTDfm9xqHV9lChoBkdAbWEby6MBIWgHTUwBaAhHQJrXwUoKD011fZQoaAZHQEDJQYUFjd5oB00IAWgIR0Ca2TOJcgQpdX2UKGgGR0A5ukY4yXUpaAdNDgFoCEdAmtqqzeGfw3V9lChoBkdAXzvfFaSs82gHTegDaAhHQJrhUxzq8lJ1fZQoaAZHwBi/rKNhmXhoB0vYaAhHQJrim9VWCEp1fZQoaAZHQGMrmw7kn1FoB03oA2gIR0Ca62OavzOHdX2UKGgGR0BwN5A3T/hmaAdNSwFoCEdAmu5gsPJ7s3V9lChoBkdAcGSfeDWbw2gHTXkBaAhHQJrwclC1JDp1fZQoaAZHv+UhvBJqZc9oB0vNaAhHQJrxljhDPWx1fZQoaAZHQG8IARsdkrhoB00qAWgIR0Ca9IEfkmx/dX2UKGgGR0A/9RaX8fmtaAdL9mgIR0Ca9eBy0a60dX2UKGgGR0Bhf/WQOnVHaAdN6ANoCEdAmvyWyC4Bm3V9lChoBkdAb86gNgBtDWgHTTYBaAhHQJr+Sogmqo91fZQoaAZHQHA8rvLHMlloB00iAWgIR0Ca/9q+JxecdX2UKGgGR0AxQqubI91VaAdL82gIR0CbAll2vB8AdX2UKGgGR0BxFdeF+NLlaAdNoQFoCEdAmwStJ4B3inV9lChoBkdAcCdmMOwxFmgHTTEBaAhHQJsGXCN0eU91fZQoaAZHQHAV/+XJHRVoB01AAWgIR0CbCT4AS39adX2UKGgGR0BKIgjQiRnwaAdL/2gIR0CbCqYkE9t/dX2UKGgGR0BiBfwI+nqFaAdN6ANoCEdAmxFwj+rEL3V9lChoBkdAOpGqYJE6UGgHS+1oCEdAmxL7ZJ04i3V9lChoBkdAb3C371qWT2gHTRQBaAhHQJsU+NbTtsx1fZQoaAZHQGWQdE9dNWVoB03oA2gIR0CbHQzySV4YdX2UKGgGR0Bwzg9W6shgaAdNOAFoCEdAmx/us90RvnV9lChoBkdANYglfJFLFmgHS91oCEdAmyEme18b73V9lChoBkdAbpvcXWOIZmgHTT4BaAhHQJsi5OJtSAJ1fZQoaAZHQG3E2CmMwURoB00kAWgIR0CbJIyad+XrdX2UKGgGR0BgRvWvr4WUaAdN6ANoCEdAmys7qhUR4HV9lChoBkdAb/5spG4I8mgHTScBaAhHQJst/Gp++dt1fZQoaAZHQDN+Tot+TeRoB0vyaAhHQJsvSj/Mnqp1fZQoaAZHQG8t/6fra/RoB01QAWgIR0CbMSw2l2vCdX2UKGgGR0BweYKNQ0oCaAdNTQFoCEdAmzQkse4kNXV9lChoBkfAO0+MAFPi1mgHS99oCEdAmzVaZ2IO6XV9lChoBkdAawYry1/lQ2gHTVoBaAhHQJs3NGiHqNZ1fZQoaAZHQFnThM8HObBoB03oA2gIR0CbPfQdS2pidX2UKGgGR0BuSFqrR0EHaAdNSQFoCEdAmz+5TqB3A3V9lChoBkdAcVdiPQv6CWgHTTUBaAhHQJtCt7sv7Fd1fZQoaAZHQG82BDgIhQpoB00pAWgIR0CbRNl67dzodX2UKGgGR0Bwgu26TW5IaAdNIwFoCEdAm0bHOKO1fHV9lChoBkdAcG4k+otL+WgHTW8BaAhHQJtK58D0UXZ1fZQoaAZHQG9nO1WsA/9oB008AWgIR0CbTKyOaOPvdX2UKGgGR0BwBUFA3T/iaAdNKwFoCEdAm05Hm/336HV9lChoBkdAQqOX7cfvF2gHS+hoCEdAm1C7Wd3B6HV9lChoBkdANZIP9UCJXWgHS+doCEdAm1H/+KjzqnV9lChoBkdAXaiKO1fE42gHTegDaAhHQJtYvCLuQZJ1fZQoaAZHQG7ob17IDHRoB03YAWgIR0CbW1QIldC3dX2UKGgGR0BFWXm3fAKwaAdNCAFoCEdAm1zNaY/mknV9lChoBkfAJJr0SRKYiWgHS7poCEdAm170QPI4l3V9lChoBkdAcOunAIppe2gHTTwBaAhHQJtguews5GV1fZQoaAZHQF7caakRBeJoB03oA2gIR0CbZ1xx1gYxdX2UKGgGR0Bhj79GZuyeaAdN6ANoCEdAm25ZWRzRyHV9lChoBkdAafOfRu0kW2gHTX8BaAhHQJtwcUcn3L51fZQoaAZHQFrvus90RvpoB03oA2gIR0CbeOZvUBn0dX2UKGgGR0Bs8IVGkN4JaAdNNQFoCEdAm3xJmqYJFHV9lChoBkdALkrsjVx0dWgHTQgBaAhHQJt9xqASWZ91fZQoaAZHwC6HNNahYeVoB0vqaAhHQJt/B80DU3J1fZQoaAZHQHBo7VOKwZBoB00qAWgIR0CbgKTBZZB+dX2UKGgGR0BwkvZOBUaRaAdNeQFoCEdAm4PnzxwyZnV9lChoBkdAa6FztkWhy2gHTTUBaAhHQJuFolkYoAp1fZQoaAZHQFq8vcrRSgpoB03oA2gIR0CbjHXEZR8/dX2UKGgGR0BsdrxXnyNGaAdNQAFoCEdAm442qgh8pnV9lChoBkdAE63I+4b0e2gHTQcBaAhHQJuQ0+KTB691fZQoaAZHQHDyCwbEP2BoB00/AWgIR0Cbkpso2GZedX2UKGgGR0BtqV3KSxJNaAdNSAFoCEdAm5Rgu/UONHV9lChoBkdAbjqreZXuE2gHTWwBaAhHQJuXf4VRDTl1fZQoaAZHQHBA9GViWmhoB00rAWgIR0CbmSZGax5cdX2UKGgGR0BuM64YrJ8waAdNLgFoCEdAm5rUpEx7A3V9lChoBkdAX7hh6Skj5mgHTegDaAhHQJuhfA8B+4N1fZQoaAZHQBW15KODJ2doB0v2aAhHQJujFDQZ4wB1fZQoaAZHQG2rOWjXWe9oB01AAWgIR0CbpsVBUrCndX2UKGgGR0A6v2aUiY9gaAdL72gIR0CbqHl54W1udX2UKGgGR0BvmcLpiZv2aAdNbwFoCEdAm6sG5hBqsXV9lChoBkdAagWYfnwG4mgHTT8BaAhHQJut5sGgSOB1fZQoaAZHQCK6Tt9hJAdoB0vjaAhHQJuvKDkELYx1fZQoaAZHQG9KBhpg1FZoB01HAWgIR0CbsPUvwmVrdX2UKGgGR0BrbXOKO1fFaAdNXwFoCEdAm7LXWSU1RHV9lChoBkdAbtXP8AJb+2gHTTQBaAhHQJu1ucAiml91fZQoaAZHwBaICuEEkjZoB0vRaAhHQJu22/etSyd1fZQoaAZHQG7mU+cH4XZoB00tAWgIR0CbuH4A0bcXdX2UKGgGR0BxbtGe+VTraAdNHAFoCEdAm7shOtW+5HV9lChoBkdAbnDDFZPl+2gHTZgBaAhHQJu9cp1A7gd1fZQoaAZHQGtbhLXcxj9oB007AWgIR0CbvyY2Kl54dX2UKGgGR0BwEwl9jPOZaAdNNgFoCEdAm8H+6/ZdwHV9lChoBkdAbs01baAWi2gHTUsBaAhHQJvD1tsN2DB1ZS4="
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 3908,
+    "_n_updates": 15632,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -84,7 +84,7 @@
     "vf_coef": 0.5,
     "max_grad_norm": 0.5,
     "batch_size": 64,
-    "n_epochs": 4,
+    "n_epochs": 16,
     "clip_range": {
         ":type:": "<class 'function'>",
         ":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a2c996919293b7f6e6191082c2ba14ff4dbe87c903d29fac81216bb44c893fd
+oid sha256:0e62721299bbdccc98e089db73e8c3f594a42bdbbac8ea02bd4042f9486a208b
 size 88362

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59641a24dd5a061c4704b16317e8daaae5a85edb2337056c8b549f2649079409
+oid sha256:f0c3b5e635ba0ab111e8cf03fc94638ef12d1ee3046b7d015a02e8136df2e14e
 size 43762

ppo-LunarLander-v2/system_info.txt

@@ -1,7 +1,7 @@
 - OS: Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023
 - Python: 3.10.12
 - Stable-Baselines3: 2.0.0a5
-- PyTorch: 2.1.0+cu121
+- PyTorch: 2.2.1+cu121
 - GPU Enabled: True
 - Numpy: 1.25.2
 - Cloudpickle: 2.2.1

results.json

@@ -1 +1 @@
-{"mean_reward": 236.62579269999998, "std_reward": 66.8326114584059, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-05T15:32:26.961617"}
+{"mean_reward": 255.62533459999995, "std_reward": 21.443103204252914, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-20T15:38:49.444228"}