Uploading PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 176.92 +/- 104.16
+      value: 281.76 +/- 20.76
       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 0x7f40ba8fbb50>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f40ba8fbbe0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f40ba8fbc70>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f40ba8fbd00>", "_build": "<function ActorCriticPolicy._build at 0x7f40ba8fbd90>", "forward": "<function ActorCriticPolicy.forward at 0x7f40ba8fbe20>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f40ba8fbeb0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f40ba8fbf40>", "_predict": "<function ActorCriticPolicy._predict at 0x7f40ba908040>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f40ba9080d0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f40ba908160>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f40ba9081f0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f40ba90c100>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1200128, "_total_timesteps": 1200000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1687955159922171461, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAABoHJD0SXaA8TCsfPuJnfr48gWE9//aEvAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -0.00010666666666669933, "_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": 4692, "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": 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-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "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 0x7f0ed2288dc0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f0ed2288e50>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f0ed2288ee0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f0ed2288f70>", "_build": "<function ActorCriticPolicy._build at 0x7f0ed2289000>", "forward": "<function ActorCriticPolicy.forward at 0x7f0ed2289090>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f0ed2289120>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f0ed22891b0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f0ed2289240>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f0ed22892d0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f0ed2289360>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f0ed22893f0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f0ed2281900>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 3000320, "_total_timesteps": 3000000.0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1688024499318050772, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAM19YD4vUVo/fUYAvaZ7u77nG1c+ul2LvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -0.00010666666666669933, "_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": 11720, "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": 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-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

ppo-MSLunarLander-v2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f499a77cb883c16fe5a5587b436c0c10b27d52787549d4b7928d139b4beaceb6
+size 146008

ppo-MSLunarLander-v2/_stable_baselines3_version

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

ppo-MSLunarLander-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 0x7f0ed2288dc0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f0ed2288e50>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f0ed2288ee0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f0ed2288f70>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f0ed2289000>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f0ed2289090>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f0ed2289120>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f0ed22891b0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f0ed2289240>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f0ed22892d0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f0ed2289360>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f0ed22893f0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f0ed2281900>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 3000320,
+    "_total_timesteps": 3000000.0,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1688024499318050772,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAM19YD4vUVo/fUYAvaZ7u77nG1c+ul2LvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -0.00010666666666669933,
+    "_stats_window_size": 100,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWV/QsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQHCh9jTa0yCMAWyUS/WMAXSUR0C2P0j+FUQ1dX2UKGgGR0Bx8jjxTbWVaAdL+2gIR0C2P+2yTpxFdX2UKGgGR0ByIF+mWMS9aAdNIwFoCEdAtkBa2hIvrXV9lChoBkdAckwC5mRNh2gHS/9oCEdAtkC436yjYnV9lChoBkdAcxkwbEP1+WgHS/xoCEdAtkEY7zTWoXV9lChoBkdAbcK4b0e2eGgHTQABaAhHQLZBwVpsXSB1fZQoaAZHQHKH3oPkJa9oB0vmaAhHQLZCF7JGOMl1fZQoaAZHQHGSaOgg5ipoB0vuaAhHQLZCbpeeFtd1fZQoaAZHQHKj7/82rGRoB0v3aAhHQLZCzlSjxkN1fZQoaAZHQG7CVvMr3CdoB0vtaAhHQLZDgCMxXXB1fZQoaAZHQGzHgo5PuXxoB00cAWgIR0C2RA1p9JBgdX2UKGgGR0Bv2Tjebd8BaAdL/2gIR0C2RI6Df3vhdX2UKGgGR0ByGHX5FgDzaAdNDAFoCEdAtkURyYG+snV9lChoBkdAcan4y44IbGgHS+hoCEdAtkX0x46fa3V9lChoBkdAcTrBqKxcFGgHTRABaAhHQLZGi9RJmNB1fZQoaAZHQHAsUkWykbhoB0v7aAhHQLZHF9mHxjJ1fZQoaAZHQHAmJGOMl1NoB0vraAhHQLZHmJk5IYp1fZQoaAZHQG7yh73PAwhoB0vwaAhHQLZIYXyAhB91fZQoaAZHQHB1YbjtG/hoB0v+aAhHQLZIvwLE1l51fZQoaAZHQHEUI8hcJMRoB0vnaAhHQLZJGNI9TxZ1fZQoaAZHQHAz2Lk0aZRoB00KAWgIR0C2SXwJkXk6dX2UKGgGR0BxVGATZg5SaAdNEQFoCEdAtkoqGfwqiHV9lChoBkdAbqq3pfQa72gHS+NoCEdAtkqE5sCT2XV9lChoBkdAcgvd7OVxCWgHTQoBaAhHQLZK5u5jH4p1fZQoaAZHQHF+54nndO9oB0vyaAhHQLZLQDCP6sR1fZQoaAZHQG/JhXCCSRtoB0vXaAhHQLZL2YcNpdt1fZQoaAZHQHHmqMaS9uhoB00zAWgIR0C2TEzh5xBFdX2UKGgGR0BuL5ZuAI6baAdL6GgIR0C2TKNd7fHhdX2UKGgGR0Bx59uYQarFaAdL4GgIR0C2TPckQf6odX2UKGgGR0BxuABhhH9WaAdL+GgIR0C2TZiAhB7edX2UKGgGR0Bxr1elbeMyaAdL+mgIR0C2TfOfNA1OdX2UKGgGR0BxnbjENvwWaAdL7GgIR0C2Tk708NhFdX2UKGgGR0BwdFKg7HQyaAdL7WgIR0C2TqYVh1DCdX2UKGgGR0BxgEujASFoaAdNIQFoCEdAtk9T6hxo7HV9lChoBkdAcUJrzXjEN2gHS+NoCEdAtk+me4Cp33V9lChoBkdAcY41R+BpYmgHS+hoCEdAtk/7hR64UnV9lChoBkdAbyCR7JGOMmgHS/loCEdAtlBXTDwYtXV9lChoBkdAcR//LDAJs2gHS/ZoCEdAtlCvVOKwZHV9lChoBkdAcnM1q33HrGgHTRMBaAhHQLZRYdZq20B1fZQoaAZHQHEbmPPszEdoB0v/aAhHQLZRvm1YyO91fZQoaAZHQG5QN9H+ZPVoB0v8aAhHQLZSIdT5wfh1fZQoaAZHQG5OLv1DjR5oB00BAWgIR0C2Up5nHvMKdX2UKGgGR0BwCQWxhUiqaAdL72gIR0C2U3QSnLq2dX2UKGgGR0BuQW63AmAtaAdNRgFoCEdAtlQS9CeEqXV9lChoBkdAcoz4gRsdk2gHS+JoCEdAtlSP4QBgeHV9lChoBkdActhhvze41GgHTQ0BaAhHQLZVk6QeV9p1fZQoaAZHQHFsH3xnWatoB0v+aAhHQLZWH/b0voN1fZQoaAZHQHIDjbah6B1oB0v2aAhHQLZWqKraM751fZQoaAZHQHA91lsguAZoB0vdaAhHQLZXCm03OwB1fZQoaAZHQGvjPEjxCppoB00NAWgIR0C2V29oJzDGdX2UKGgGR0BxOTUkOZssaAdNDwFoCEdAtlgfIV/MGHV9lChoBkdAc0vRjz7MxGgHTQ8BaAhHQLZYgpgTh5x1fZQoaAZHQGDe/BWPtD5oB03oA2gIR0C2Wj2/JvHcdX2UKGgGR0ByFWF36hxpaAdNmgNoCEdAtlvcLDye7XV9lChoBkdAb+lXHR1HOWgHS9NoCEdAtlwqbhFVk3V9lChoBkdAcTsWJaaCtmgHS+9oCEdAtlyKuJUHZHV9lChoBkdAcIlgdwNsnGgHS/RoCEdAtl0uJiy6c3V9lChoBkdAb7j84PwuumgHS+BoCEdAtl2DEaVD8nV9lChoBkdAcz/XqJMxoWgHS9doCEdAtl3R5Pdl/nV9lChoBkdAcXtF23azvGgHS+doCEdAtl4nb8FY+3V9lChoBkdAcAwZWq94/2gHS/9oCEdAtl6DRiPQwHV9lChoBkdAcaW5E+gUUWgHS/poCEdAtl8pZ4fOlnV9lChoBkdAcBtAAQxvemgHS/ZoCEdAtl+DRNRFZ3V9lChoBkdAcfcKBun/DWgHS/ZoCEdAtl/gHlfZ3HV9lChoBkdAcKRUornTzGgHS+5oCEdAtmA3d+G47XV9lChoBkdAMk9FfAsTWWgHS7hoCEdAtmDMMoc7yXV9lChoBkdAcgOpb2USqWgHS9doCEdAtmEysLfDUHV9lChoBkdAcicxUvPC22gHTeMDaAhHQLZjjU96kZd1fZQoaAZHQHPW2bb1yvNoB0vKaAhHQLZj/AgxJul1fZQoaAZHQHCfbF4s3AFoB0vzaAhHQLZkgZdv8651fZQoaAZHQG7sqKpDNQloB00kAWgIR0C2ZYvEsJ6ZdX2UKGgGR0Bx1g7q6e5GaAdNFwFoCEdAtmX/4QBgeHV9lChoBkdAcJslNUOuq2gHS/ZoCEdAtmZcFA3T/nV9lChoBkdAcPVK6WgOBmgHS/1oCEdAtma4V2zOX3V9lChoBkdAcCdE+PikwmgHS+VoCEdAtmcK6g/Ts3V9lChoBkdAbO2bcXWOImgHS/VoCEdAtmeqqsEJSnV9lChoBkdAcAIRJ2+wkmgHS/5oCEdAtmgJGEwnIHV9lChoBkdAcvtRZ2ZAp2gHTRgBaAhHQLZocBFd9lV1fZQoaAZHQHAoI4ACGN9oB0vnaAhHQLZow0jTrmh1fZQoaAZHQHGJqjafzz5oB00CAWgIR0C2aW6LbYbsdX2UKGgGR0BxAQ+HJtBOaAdNEwFoCEdAtmnT/VAiV3V9lChoBkdAcYZOoHcDbWgHS/RoCEdAtmotiZv1lHV9lChoBkdAcjJmEXcgyWgHS/FoCEdAtmqFdgOSXHV9lChoBkdAb6Brs0HhTGgHS+NoCEdAtmsciUxEfHV9lChoBkdAceR2xIJ7cGgHTQQBaAhHQLZre1OTJQt1fZQoaAZHQHD1VOwgTytoB0v0aAhHQLZr1+HrQgN1fZQoaAZHQHDkGax5cC5oB0v5aAhHQLZsNfk3juN1fZQoaAZHQHDBOVLSNOxoB0vsaAhHQLZs1oZAIIF1fZQoaAZHQHE3MvZh8Y1oB0vYaAhHQLZtKFfiPyV1fZQoaAZHQHL4b/n4fwJoB00IAWgIR0C2bY6A4GUwdX2UKGgGR0Bw3PmT1TR6aAdL32gIR0C2beCJfpljdX2UKGgGR0BwaxNucc2jaAdL+GgIR0C2boHIlt0ndX2UKGgGR0ByD/XI2fkFaAdL3GgIR0C2btH+IdlvdX2UKGgGR0BwNyFcpsoEaAdNJwFoCEdAtm8/WEsasXV9lChoBkdAcvpAxSHdoGgHS9hoCEdAtm+OscQyynV9lChoBkdAcjCo5PuXu2gHTRABaAhHQLZwbEuQIUt1fZQoaAZHQHBUyjQAuI1oB0vwaAhHQLZw4iQ1aW51fZQoaAZHQG/hTOX3QD5oB0vaaAhHQLZxTEG7jDN1fZQoaAZHQFY//yoXKr9oB0u9aAhHQLZxp2K2rn11fZQoaAZHQHL4j8LrontoB0voaAhHQLZyIqbz9TB1ZS4="
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 11720,
+    "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": 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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"
+    }
+}

ppo-MSLunarLander-v2/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07805eb3cce7f07776b57d5b8336ce8d4827e09fa5494b9e0edf0ad3dd3bb3a1
+size 87929

ppo-MSLunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2962d6c1bcf4d53b041a31ed05500064da2b96d4d78c66d2c487e1024b3c23c8
+size 43329

ppo-MSLunarLander-v2/pytorch_variables.pth

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

ppo-MSLunarLander-v2/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023
+- Python: 3.10.12
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.0.1+cu118
+- GPU Enabled: True
+- Numpy: 1.22.4
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.25.2

results.json

@@ -1 +1 @@
-{"mean_reward": 176.9191086, "std_reward": 104.16107963066337, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-06-28T13:06:00.529739"}
+{"mean_reward": 281.7624768, "std_reward": 20.75866894201727, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-06-29T09:22:04.749858"}