Upload PPO LunarLander-v2 trained agent

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: -141.67 +/- 40.61
+      value: 261.66 +/- 18.18
       name: mean_reward
     task:
       type: reinforcement-learning

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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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 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 0x7f3a7d175f80>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f3a7d17d050>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f3a7d17d0e0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f3a7d17d170>", "_build": "<function ActorCriticPolicy._build at 0x7f3a7d17d200>", "forward": "<function ActorCriticPolicy.forward at 0x7f3a7d17d290>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f3a7d17d320>", "_predict": "<function ActorCriticPolicy._predict at 0x7f3a7d17d3b0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f3a7d17d440>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f3a7d17d4d0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f3a7d17d560>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f3a7d1bdc90>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1024, "num_timesteps": 2097152, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1651758722.7615552, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAQAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYABAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiTQAEhZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.04857599999999995, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 8, "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:": "gAWVvwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
+{"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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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 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 0x7fb8ddb7a5f0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb8ddb7a680>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb8ddb7a710>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb8ddb7a7a0>", "_build": "<function ActorCriticPolicy._build at 0x7fb8ddb7a830>", "forward": "<function ActorCriticPolicy.forward at 0x7fb8ddb7a8c0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb8ddb7a950>", "_predict": "<function ActorCriticPolicy._predict at 0x7fb8ddb7a9e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb8ddb7aa70>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb8ddb7ab00>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb8ddb7ab90>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fb8ddbbdc00>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 96, "num_timesteps": 2064384, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1652222077.493272, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWV0wAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZgAAAAAAAAAAAAAAAAAAAAAQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLYIWUjAFDlHSUUpQu"}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.032192, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 168, "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": 8, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e76864629afd68ae5fed33dbe55790a6a75e12918ae97eeecb573f6807cbaead
-size 188333
+oid sha256:1051bd51db4157ec7a627563cd127931a16f52e0e40ba50ee0b8417c80b017ec
+size 147613

ppo-LunarLander-v2/data

@@ -4,19 +4,19 @@
         ":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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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 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 0x7f3a7d175f80>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f3a7d17d050>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f3a7d17d0e0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f3a7d17d170>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f3a7d17d200>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f3a7d17d290>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f3a7d17d320>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f3a7d17d3b0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f3a7d17d440>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f3a7d17d4d0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f3a7d17d560>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7fb8ddb7a5f0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb8ddb7a680>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb8ddb7a710>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb8ddb7a7a0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fb8ddb7a830>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fb8ddb7a8c0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb8ddb7a950>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fb8ddb7a9e0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb8ddb7aa70>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb8ddb7ab00>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb8ddb7ab90>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7f3a7d1bdc90>"
+        "_abc_impl": "<_abc_data object at 0x7fb8ddbbdc00>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -41,13 +41,13 @@
         "dtype": "int64",
         "_np_random": null
     },
-    "n_envs": 1024,
-    "num_timesteps": 2097152,
+    "n_envs": 96,
+    "num_timesteps": 2064384,
     "_total_timesteps": 2000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1651758722.7615552,
+    "start_time": 1652222077.493272,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "lr_schedule": {
@@ -56,26 +56,26 @@
     },
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVdAQAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYABAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiTQAEhZSMAUOUdJRSlC4="
+        ":serialized:": "gAWV0wAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZgAAAAAAAAAAAAAAAAAAAAAQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLYIWUjAFDlHSUUpQu"
     },
     "_last_original_obs": null,
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.04857599999999995,
+    "_current_progress_remaining": -0.032192,
     "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": 8,
+    "_n_updates": 168,
     "n_steps": 1024,
     "gamma": 0.999,
     "gae_lambda": 0.98,
@@ -83,7 +83,7 @@
     "vf_coef": 0.5,
     "max_grad_norm": 0.5,
     "batch_size": 64,
-    "n_epochs": 4,
+    "n_epochs": 8,
     "clip_range": {
         ":type:": "<class 'function'>",
         ":serialized:": "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"

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b303dba5f95837aabc886446c27ad5b225301d2824e2f3c006c57c00e54988a
+oid sha256:d88cb96bd5cb5afb736e2fea30438ece093deb538d2b3840a09cb4c35d9f946d
 size 84893

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a33c08c82f08f3da19f216c2fe27ff798142b8a7943fdb635ad273b3969dcec8
+oid sha256:7d0da9353a81502580820c140c935db0cb0893a8fee565416ca7e15333011a09
 size 43201

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f852ea287c2cc0a3ccba4ea012b09721530622c1629cd4c86ad79c81a49e63eb
-size 253943
+oid sha256:031c673569eb40de96e715a30ca03deb2baa32fd2ef15e3d7b4fa21d98e7e9a5
+size 205592

results.json

@@ -1 +1 @@
-{"mean_reward": -141.66860129119596, "std_reward": 40.6133855839029, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-05T14:16:29.289943"}
+{"mean_reward": 261.6631750020884, "std_reward": 18.177438838726417, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-10T23:24:35.560982"}