Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -293.02 +/- 191.57
+      value: 266.26 +/- 17.56
       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 0x7a8b1ef9a050>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7a8b1ef9a0e0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7a8b1ef9a170>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7a8b1ef9a200>", "_build": "<function ActorCriticPolicy._build at 0x7a8b1ef9a290>", "forward": "<function ActorCriticPolicy.forward at 0x7a8b1ef9a320>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7a8b1ef9a3b0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7a8b1ef9a440>", "_predict": "<function ActorCriticPolicy._predict at 0x7a8b1ef9a4d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7a8b1ef9a560>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7a8b1ef9a5f0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7a8b1ef9a680>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7a8b1ef9d280>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1024, "_total_timesteps": 100, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1691106246541760373, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAGZm3byjBcE/m9BHvhqtIz6ZW5o8MnuLPQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -9.24, "_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": 4, "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-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 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 0x7eff4dcb3e20>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7eff4dcb3eb0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7eff4dcb3f40>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7eff4dcc8040>", "_build": "<function ActorCriticPolicy._build at 0x7eff4dcc80d0>", "forward": "<function ActorCriticPolicy.forward at 0x7eff4dcc8160>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7eff4dcc81f0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7eff4dcc8280>", "_predict": "<function ActorCriticPolicy._predict at 0x7eff4dcc8310>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7eff4dcc83a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7eff4dcc8430>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7eff4dcc84c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7eff4dcc0fc0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1000448, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1691107818836134613, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAJrW1b2PPim6pQnQOSLhaTQtjVe6ulX2uAAAAAAAAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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:": "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-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 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-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a1ad30291dc7ab49b60f026405e30554d42f7d044f2a853af2860e7b3f619cc
-size 142416
+oid sha256:4f7bde66f518b21de08a629450c2292feb47fb84f4b4950e771fa356b352da21
+size 146068

ppo-LunarLander-v2/data

@@ -4,34 +4,34 @@
         ":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 0x7a8b1ef9a050>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7a8b1ef9a0e0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7a8b1ef9a170>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7a8b1ef9a200>",
-        "_build": "<function ActorCriticPolicy._build at 0x7a8b1ef9a290>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7a8b1ef9a320>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7a8b1ef9a3b0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7a8b1ef9a440>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7a8b1ef9a4d0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7a8b1ef9a560>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7a8b1ef9a5f0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7a8b1ef9a680>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7eff4dcb3e20>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7eff4dcb3eb0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7eff4dcb3f40>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7eff4dcc8040>",
+        "_build": "<function ActorCriticPolicy._build at 0x7eff4dcc80d0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7eff4dcc8160>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7eff4dcc81f0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7eff4dcc8280>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7eff4dcc8310>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7eff4dcc83a0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7eff4dcc8430>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7eff4dcc84c0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7a8b1ef9d280>"
+        "_abc_impl": "<_abc._abc_data object at 0x7eff4dcc0fc0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 1024,
-    "_total_timesteps": 100,
+    "num_timesteps": 1000448,
+    "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1691106246541760373,
+    "start_time": 1691107818836134613,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAGZm3byjBcE/m9BHvhqtIz6ZW5o8MnuLPQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAJrW1b2PPim6pQnQOSLhaTQtjVe6ulX2uAAAAAAAAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -41,17 +41,17 @@
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -9.24,
+    "_current_progress_remaining": -0.00044800000000000395,
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 4,
+    "_n_updates": 3908,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "gAWVcAIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoECiWCAAAAAAAAAABAQEBAQEBAZRoFEsIhZRoGHSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBAoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaApLCIWUaBh0lFKUjARoaWdolGgQKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgKSwiFlGgYdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=",

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9b39f1b187bbf7368f32c6448afda92cfa672ff2e83aff9ca414c447d54b19d
+oid sha256:e0a00dc0c49a602c09697be78bb25b728f4dd2d60a16042a0c3d436546c96f51
 size 87929

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:987fd1ba5389d63a16b6cc052d1f94f5b2851c1732231c05f867760a86bbb112
+oid sha256:33f40fd45fefea972993de8ea3c1d9810cbdfccbcf47d84627839271f58947e4
 size 43329

results.json

@@ -1 +1 @@
-{"mean_reward": -293.0246506841853, "std_reward": 191.56895756229838, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-08-03T23:52:49.775883"}
+{"mean_reward": 266.2604028517552, "std_reward": 17.562288119608564, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-08-04T00:43:44.372605"}