Upload of improved PPO model on LunarLander-v2

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -509.44 +/- 112.72
+      value: 258.66 +/- 14.59
       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 0x7fad23a74940>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fad23a749d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fad23a74a60>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fad23a74af0>", "_build": "<function ActorCriticPolicy._build at 0x7fad23a74b80>", "forward": "<function ActorCriticPolicy.forward at 0x7fad23a74c10>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fad23a74ca0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fad23a74d30>", "_predict": "<function ActorCriticPolicy._predict at 0x7fad23a74dc0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fad23a74e50>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fad23a74ee0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fad23a74f70>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fad23a65880>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 0, "_total_timesteps": 0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 0.0, "learning_rate": 0.0003, "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, "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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 2048, "gamma": 0.98, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 128, "n_epochs": 10, "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-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.23.5", "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 0x7fad23a74940>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fad23a749d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fad23a74a60>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fad23a74af0>", "_build": "<function ActorCriticPolicy._build at 0x7fad23a74b80>", "forward": "<function ActorCriticPolicy.forward at 0x7fad23a74c10>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fad23a74ca0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fad23a74d30>", "_predict": "<function ActorCriticPolicy._predict at 0x7fad23a74dc0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fad23a74e50>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fad23a74ee0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fad23a74f70>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fad23a65880>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1696518856065072460, "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:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "_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": 248, "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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "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:": "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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-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

ppo-LunarLander-v2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90906ad61c9ad8219c63b8ef08f9bdc8192e99cf6d0dc8c95c2c19fb7cfd9c23
+size 146755

ppo-LunarLander-v2/_stable_baselines3_version

@@ -0,0 +1 @@
+2.0.0a5

ppo-LunarLander-v2/data

@@ -0,0 +1,99 @@
+{
+    "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 0x7fad23a74940>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fad23a749d0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fad23a74a60>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fad23a74af0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fad23a74b80>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fad23a74c10>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fad23a74ca0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fad23a74d30>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fad23a74dc0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fad23a74e50>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fad23a74ee0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fad23a74f70>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fad23a65880>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1696518856065072460,
+    "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:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": null,
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.015808000000000044,
+    "_stats_window_size": 100,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVQgwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQHAoeXVsk6eMAWyUTdYCjAF0lEdAmH7lKTSssHV9lChoBkdAYgqiEg4ffWgHTegDaAhHQJiB/E61b7l1fZQoaAZHQGbm32VVxS5oB03oA2gIR0CYho+n62v0dX2UKGgGR0BkTvsgMc6vaAdN6ANoCEdAmI0zlxOtXHV9lChoBkdAcGQZHNHH3mgHTX0DaAhHQJiN8xzq8lJ1fZQoaAZHQGNpWDg62fFoB03oA2gIR0CYjqLR8c+8dX2UKGgGR0BhQGE/SpiraAdN6ANoCEdAmKlRF3IMjXV9lChoBkdAcEJI42jwhGgHTdQBaAhHQJiqGcoYvWZ1fZQoaAZHv/Sh+vyLAHpoB007AWgIR0CYqi8QqZtvdX2UKGgGR0BF8Auyu6mPaAdLzmgIR0CYq1vegte2dX2UKGgGR0Bk8oXoC+10aAdN6ANoCEdAmKuh1s+FDnV9lChoBkdAcIGkiUxEfGgHTV8CaAhHQJisSjGkvbp1fZQoaAZHQHBq2hufmLdoB03/AWgIR0CYsOaxHG0edX2UKGgGR0BknwKMNtqIaAdN6ANoCEdAmLI3vc8DCHV9lChoBkdAPUcSwnpjc2gHTQABaAhHQJiynci4axZ1fZQoaAZHQGUZfRNRFZxoB03oA2gIR0CYt/KTSsr/dX2UKGgGR0BFbejua4MGaAdNNAFoCEdAmLkcVDa4+nV9lChoBkdAZceUypJf6WgHTegDaAhHQJjAzCJoCdV1fZQoaAZHQGZytTDO1OVoB03oA2gIR0CYwjOLzf78dX2UKGgGR0Bg/3MGHHmzaAdN6ANoCEdAmMLsQmNR33V9lChoBkdAcX7C/XXiBGgHTS0DaAhHQJjHK3G4qgB1fZQoaAZHQG0bmQbMottoB01JAmgIR0CYyVlmOEM9dX2UKGgGR0Bvbx/ViF0xaAdNgAJoCEdAmM1YHLRrrXV9lChoBkdAa02nssxwhmgHTe4CaAhHQJjRw7Omixp1fZQoaAZHQHLyDXjENvxoB01JAWgIR0CY1ZC7btZ3dX2UKGgGR0ByFlWOp84QaAdNlwJoCEdAmNcQ8nuy/3V9lChoBkdAYZNlqagElmgHTegDaAhHQJje2HqNZNh1fZQoaAZHQGWPdDIBBAxoB03oA2gIR0CY37IkZ75VdX2UKGgGR0Bm20Y0l7dBaAdN6ANoCEdAmPpWL9/BnHV9lChoBkdAYtSUwBYFJWgHTegDaAhHQJj69bqyGBZ1fZQoaAZHQG90OLR8c+9oB03UAWgIR0CY/Cxd6cAjdX2UKGgGR0BtMIAuIyj6aAdNhAJoCEdAmP80/4ZdfXV9lChoBkdAbz4P8Q7LdWgHTcwBaAhHQJj/jMotthx1fZQoaAZHQF/zUzKs+3ZoB03oA2gIR0CZAEy2hIvrdX2UKGgGR0Bq9KROk+HKaAdNyANoCEdAmQCY/eLvTnV9lChoBkdAb6JyBkI5YGgHTZYBaAhHQJkE/tnf2sd1fZQoaAZHQG0FGmDUVi5oB00bA2gIR0CZBUhRZU1idX2UKGgGR0Bj7ygTRIBjaAdN6ANoCEdAmQe6K+BYm3V9lChoBkdAZ+6VHFxXGWgHTegDaAhHQJkI6E4//vR1fZQoaAZHQHF/jLB9Cu5oB00mAWgIR0CZCd/20zCUdX2UKGgGR0BwHyV9nbqRaAdNoQFoCEdAmQtm+fywwHV9lChoBkdAMbIduHerMmgHS/hoCEdAmQyp1mrbQHV9lChoBkdAb7ky4Wk8BGgHTVYCaAhHQJkOACyQgcN1fZQoaAZHQG5MGYa5wwVoB02sAmgIR0CZDuLfk3judX2UKGgGR0BvMDZzxPO6aAdNfgNoCEdAmQ+539rGi3V9lChoBkdAcEyHz6JqI2gHTTUCaAhHQJkR7ysjmjl1fZQoaAZHQHAtEE9t/F1oB02gAWgIR0CZFY1fVqetdX2UKGgGR0BwfdrhzeXSaAdNQwFoCEdAmRXm9xp+MXV9lChoBkdAchbQVsUIs2gHTdoBaAhHQJkXeNrCWNZ1fZQoaAZHQHGVqNdZ7oloB01sAWgIR0CZGD6nivPkdX2UKGgGR0Bw9dDb8FY/aAdN8gFoCEdAmRl9Dpkf93V9lChoBkdAcIDf7rLQomgHTTsBaAhHQJkZ5u4wyqN1fZQoaAZHQDF8J+lTFVFoB00FAWgIR0CZGvnAqNIcdX2UKGgGR0BvH8jHGS6laAdNTQFoCEdAmSD6STyJ9HV9lChoBkdAcLsRlpXZG2gHTbcBaAhHQJki4ka/ATJ1fZQoaAZHQHGDdrsSkCVoB03cAWgIR0CZJ/xyn1nNdX2UKGgGR0AROAkLQXyiaAdNAgFoCEdAmSszAaef7XV9lChoBkdAcCBllbu+iGgHTdUBaAhHQJksNHSWqtJ1fZQoaAZHQHEdMFt8/lhoB02SAWgIR0CZLE3Ytg8bdX2UKGgGR0BykOlDWsijaAdNSgFoCEdAmTAWuPmxMXV9lChoBkdAcQvcclw97mgHTdoCaAhHQJlESs1baAZ1fZQoaAZHQGFuFBQemvZoB03oA2gIR0CZRJ2d/axpdX2UKGgGR0Bs8Z3kgfU4aAdNyANoCEdAmUSdVNpM6HV9lChoBkdAcbRbQ1JlKGgHTbQBaAhHQJlFJKDkELZ1fZQoaAZHQHEdB5ooNNJoB03aAWgIR0CZRUTq0MPSdX2UKGgGR0Br/hEtuk1uaAdNQgFoCEdAmUZLwWnCO3V9lChoBkdAckcWOZLIxWgHTdABaAhHQJlHVyBClad1fZQoaAZHQG6XZ5AyEctoB00PAmgIR0CZSEY3eenRdX2UKGgGR0By9Imw7kn1aAdNdgFoCEdAmUwg8B+4LHV9lChoBkdAbZMbPyCnP2gHTY4CaAhHQJlMU8vEjxF1fZQoaAZHQHC1wY+B6KNoB01UAWgIR0CZTUzbN8mbdX2UKGgGR0Bw70Sg5BC2aAdNeAFoCEdAmU39U0elsXV9lChoBkdAbkJsY2sJY2gHTWUBaAhHQJlOG7SRbKR1fZQoaAZHQHADh7u2JBRoB00HAmgIR0CZT4LwWnCPdX2UKGgGR0BwO7JCBwuNaAdNgANoCEdAmVHdqYZ2p3V9lChoBkdAcNGK5TZQHmgHTVsBaAhHQJlS7bi6xxF1fZQoaAZHQBsG5lOGj9JoB00hAWgIR0CZU9HYpUgkdX2UKGgGR0BxJ6NedCmeaAdNWQFoCEdAmVPvUONHY3V9lChoBkdAcRvhnanJk2gHTW8BaAhHQJlVTOiWVu91fZQoaAZHQHKe7u+h4+toB02bAWgIR0CZVvqgAZKndX2UKGgGR0Bxo7O+qR2baAdNSQFoCEdAmVdkcXFcZHV9lChoBkdAcvyQbuMMqmgHTakBaAhHQJlXujTKDCh1fZQoaAZHQHBszHXEqDtoB03lAWgIR0CZXeFA3T/idX2UKGgGR0BwhmP/7zkIaAdNJgFoCEdAmV30WykbgnV9lChoBkdAb4qGKQ7tA2gHTVsBaAhHQJlev1RLsa91fZQoaAZHQG5A5LAYYSBoB01eAWgIR0CZYI580DU3dX2UKGgGR0BrMYnpjc2zaAdNdwJoCEdAmWHu+dsi0XV9lChoBkdAbB4gieNDMWgHTZ4BaAhHQJljAtHxz7x1fZQoaAZHQGqbL5ylvZRoB03BAWgIR0CZazMdcSoPdX2UKGgGR0Bwu4Tj/+85aAdN8AFoCEdAmWvoH1OCXnV9lChoBkdAbLbqTr3TNWgHTVoBaAhHQJlt2fra/RF1fZQoaAZHQHE15NoJzDJoB01cAWgIR0CZbseHSF4+dX2UKGgGR0BwawnH/95yaAdN1QFoCEdAmW+hegL7XXV9lChoBkdAbfinfEXLvGgHTbgBaAhHQJlwDsgMc6x1fZQoaAZHQG25I8yN4qxoB03QAWgIR0CZcILdepn6dX2UKGgGR0BtTWwu/UONaAdNzAFoCEdAmXI0WuX/pHV9lChoBkdAcRjoXsPatmgHTTwBaAhHQJlyNVR1oxp1fZQoaAZHQGziKcmShaloB01bAWgIR0CZdBFj/dZadX2UKGgGR0BwbU7W/ag3aAdNIQJoCEdAmXTedXko4XV9lChoBkdAbgLUfgaWHGgHTe8BaAhHQJl1fiR4hU11ZS4="
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 248,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "gAWVcAIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoECiWCAAAAAAAAAABAQEBAQEBAZRoFEsIhZRoGHSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBAoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaApLCIWUaBh0lFKUjARoaWdolGgQKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgKSwiFlGgYdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=",
+        "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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=",
+        "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:": "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"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    }
+}

ppo-LunarLander-v2/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a23a769d2e093d6a17151e5cfc7f1582b58ba8aaed12aaac35934faaeb4ac3a
+size 87929

ppo-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90cd0ecf1a322614a45d605e1e1c6661541494497e71072a8a2ce1b5e91d4c5b
+size 43329

ppo-LunarLander-v2/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
+size 431

ppo-LunarLander-v2/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023
+- Python: 3.10.12
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.0.1+cu118
+- GPU Enabled: True
+- Numpy: 1.23.5
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.25.2

results.json

@@ -1 +1 @@
-{"mean_reward": -509.4384649019688, "std_reward": 112.71612114903128, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-10-05T14:55:57.316643"}
+{"mean_reward": 258.6642019417627, "std_reward": 14.590852434007521, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-10-05T15:40:36.622069"}