Upload PPO LunarLander-v2 1e6 default trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -124.87 +/- 34.55
+      value: -162.67 +/- 61.54
       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 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 0x7fa5ed6f6b80>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fa5ed6f6c10>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fa5ed6f6ca0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fa5ed6f6d30>", "_build": "<function ActorCriticPolicy._build at 0x7fa5ed6f6dc0>", "forward": "<function ActorCriticPolicy.forward at 0x7fa5ed6f6e50>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fa5ed6f6ee0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fa5ed6f6f70>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fa5ed6fa040>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fa5ed6fa0d0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fa5ed6fa160>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fa5ed6d8d20>"}, "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": 16, "num_timesteps": 0, "_total_timesteps": 0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": null, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_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, "ep_info_buffer": null, "ep_success_buffer": null, "_n_updates": 0, "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, "system_info": {"OS": "Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu116", "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 0x7fbc50cebc10>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fbc50cebca0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fbc50cebd30>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fbc50cebdc0>", "_build": "<function ActorCriticPolicy._build at 0x7fbc50cebe50>", "forward": "<function ActorCriticPolicy.forward at 0x7fbc50cebee0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fbc50cebf70>", "_predict": "<function ActorCriticPolicy._predict at 0x7fbc50cf0040>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fbc50cf00d0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fbc50cf0160>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fbc50cf01f0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fbc50ce8e40>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "gAWVnwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAAAAAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/5RoCksIhZSMAUOUdJRSlIwEaGlnaJRoEiiWIAAAAAAAAAAAAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAf5RoCksIhZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolggAAAAAAAAAAAAAAAAAAACUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLCIWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYIAAAAAAAAAAAAAAAAAAAAlGghSwiFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu", "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": 16, "num_timesteps": 212992, "_total_timesteps": 200000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1671380949087190696, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAADOdBDxxtRK7KCnWPC13zLz7udi7mQSyvQAAgD8AAIA/3ownvzfTbL0EbxO5utwsN0+rHL7K3kY4AACAPwAAgD/ta4s+3LeaP5YuBj929Lm+LjSbPi4NUD4AAAAAAAAAAGai1DyDd84+mu4gvnJaq760Pog+DrD3PQAAAAAAAAAAzc+IvexzmDrj9/47JQWIvMYe+zu6GDw9AAAAAAAAAAAzAtc85C6cP6Jojz12N7C+kqZrPS4CBD4AAAAAAAAAAMNjjD5xQ4g/MH3vvU17Hr+0kAI/w60svgAAAAAAAAAADbm7vY8+EbomIvM5g6xtNa3oKbpCpw65AACAPwAAgD8dZ/K+seEDvRWfkTwxq2i6WOuevLqNhzwAAAAAAAAAAE0q+T1EsIc/cJCePbPO275fLIU+aGuOPQAAAAAAAAAAGtSuvRTWtbq13VE8KmfQvPVfCjzUe7g9AAAAAAAAgD810Y6+0uaPPF2u1z3F8JS8CmodvYhbKr0AAAAAAACAP9POQb5xSK0/Gngiv4vNqL67A629+AsdvgAAAAAAAAAAWxfWvvwYFj1uof25JgfQNwOlar2otBU5AACAPwAAgD+0Gk+/7h7cvN7/Fr5yWxm9FNfbPb5JoL4AAAAAAACAPxAXXr7ef7g/2HQlv/0+er76LKs8cw0qvgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="}, "_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": -0.0649599999999999, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 52, "n_steps": 1024, "gamma": 0.995, "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, "system_info": {"OS": "Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu116", "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 sha256:3b0336b2822e1a3643a7a9fb24e9e3555353242467135d6cfaf3d7e05f61c268
-size 52863
+oid sha256:d60838ea4fb3af9565b3db364166b80504ab5781c6a53f8f8b685f0246ebb506
+size 147089

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 0x7fa5ed6f6b80>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fa5ed6f6c10>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fa5ed6f6ca0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fa5ed6f6d30>",
-        "_build": "<function ActorCriticPolicy._build at 0x7fa5ed6f6dc0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7fa5ed6f6e50>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fa5ed6f6ee0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7fa5ed6f6f70>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fa5ed6fa040>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fa5ed6fa0d0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fa5ed6fa160>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7fbc50cebc10>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fbc50cebca0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fbc50cebd30>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fbc50cebdc0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fbc50cebe50>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fbc50cebee0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fbc50cebf70>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fbc50cf0040>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fbc50cf00d0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fbc50cf0160>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fbc50cf01f0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7fa5ed6d8d20>"
+        "_abc_impl": "<_abc_data object at 0x7fbc50ce8e40>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -42,30 +42,42 @@
         "_np_random": null
     },
     "n_envs": 16,
-    "num_timesteps": 0,
-    "_total_timesteps": 0,
+    "num_timesteps": 212992,
+    "_total_timesteps": 200000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": null,
+    "start_time": 1671380949087190696,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "lr_schedule": {
         ":type:": "<class 'function'>",
         ":serialized:": "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"
     },
-    "_last_obs": null,
-    "_last_episode_starts": 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": 1,
-    "ep_info_buffer": null,
-    "ep_success_buffer": null,
-    "_n_updates": 0,
+    "_current_progress_remaining": -0.0649599999999999,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVJBAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBHCzeLF4JUCUhpRSlIwBbJRLnIwBdJRHQIEOsGmk30h1fZQoaAZoCWgPQwgRHQJHAk06QJSGlFKUaBVLiWgWR0CBD5SThYNidX2UKGgGaAloD0MICtgORuxTLECUhpRSlGgVS75oFkdAgQ/cP4EfT3V9lChoBmgJaA9DCC7kEdxIaR7AlIaUUpRoFUt7aBZHQIERg/C66J91fZQoaAZoCWgPQwjPSIRGsAk5wJSGlFKUaBVLmWgWR0CBEX4LThHcdX2UKGgGaAloD0MIATPfwU+wQ8CUhpRSlGgVS2doFkdAgRGUNz8xbnV9lChoBmgJaA9DCJkoQup2ukpAlIaUUpRoFU3oA2gWR0CBEvOzposadX2UKGgGaAloD0MIkC3L12XsQUCUhpRSlGgVS4ZoFkdAgRU43FUADXV9lChoBmgJaA9DCBOe0OtPsifAlIaUUpRoFUuPaBZHQIEVYr+YMOR1fZQoaAZoCWgPQwjj3vyGib4gQJSGlFKUaBVLg2gWR0CBFiN3GGVSdX2UKGgGaAloD0MI14UfnE8jQcCUhpRSlGgVS7toFkdAgRZGqo60Y3V9lChoBmgJaA9DCBObj2tDuTxAlIaUUpRoFUuWaBZHQIEWaJj2Bat1fZQoaAZoCWgPQwghAaPLmyMqQJSGlFKUaBVLmmgWR0CBFpLlFMIvdX2UKGgGaAloD0MI4QfnU8cqrT+UhpRSlGgVS2loFkdAgRiRFAmiQHV9lChoBmgJaA9DCJ8dcF0xcxRAlIaUUpRoFUuiaBZHQIEYpStNi6R1fZQoaAZoCWgPQwjLuRRXlaNJQJSGlFKUaBVLiWgWR0CBGQRZlnRLdX2UKGgGaAloD0MIzO80mfE2IkCUhpRSlGgVS6hoFkdAgRkshgVoH3V9lChoBmgJaA9DCLvvGB77sS/AlIaUUpRoFUuVaBZHQIEZmO+7Dl51fZQoaAZoCWgPQwjyQ6URM41CQJSGlFKUaBVLsmgWR0CBG0k30f5ldX2UKGgGaAloD0MI5IQJo1npRMCUhpRSlGgVS3xoFkdAgRws90RvnHV9lChoBmgJaA9DCAOxbOaQXDfAlIaUUpRoFUtsaBZHQIEcLbi6xxF1fZQoaAZoCWgPQwjlJ9U+HechQJSGlFKUaBVLeWgWR0CBHMXOW0JGdX2UKGgGaAloD0MI5L9AECCD+r+UhpRSlGgVS6VoFkdAgR5fRE4NqnV9lChoBmgJaA9DCNS6DWq/10rAlIaUUpRoFUuZaBZHQIEe9M/QjUx1fZQoaAZoCWgPQwikx+9t+iMaQJSGlFKUaBVLqWgWR0CBIChq0tyxdX2UKGgGaAloD0MI4297gsR2hz+UhpRSlGgVS31oFkdAgSA43m3fAXV9lChoBmgJaA9DCDhLyXISPjRAlIaUUpRoFUuJaBZHQIEgiF/QSjB1fZQoaAZoCWgPQwioVImytxTnP5SGlFKUaBVLhWgWR0CBIW8jAzpHdX2UKGgGaAloD0MIqG4u/rbHHUCUhpRSlGgVS3BoFkdAgSMDB2wFDHV9lChoBmgJaA9DCDMyyF2E6Q5AlIaUUpRoFUt0aBZHQIEjQ371qWV1fZQoaAZoCWgPQwjNdoU+WAY5QJSGlFKUaBVLi2gWR0CBI7cUuctodX2UKGgGaAloD0MILAyR09fXMMCUhpRSlGgVS2loFkdAgSUE6T4cm3V9lChoBmgJaA9DCBXGFoIchVpAlIaUUpRoFU3oA2gWR0CBJTylvZRLdX2UKGgGaAloD0MI9TC0OjlD0L+UhpRSlGgVS8poFkdAgSVIYNy5qnV9lChoBmgJaA9DCIqT+x2KAtA/lIaUUpRoFUuCaBZHQIEm+c+aBqd1fZQoaAZoCWgPQwiEukihLMQywJSGlFKUaBVLtWgWR0CBJ9hP0qYrdX2UKGgGaAloD0MIAFeyYyNUO0CUhpRSlGgVS39oFkdAgSgA1Nxlx3V9lChoBmgJaA9DCCO9qN2vAhRAlIaUUpRoFUuJaBZHQIEoj7oB7u51fZQoaAZoCWgPQwiDT3PyInspwJSGlFKUaBVLlmgWR0CBTgsZHd43dX2UKGgGaAloD0MItd/aiZKoNMCUhpRSlGgVS5JoFkdAgU6pwsGxEHV9lChoBmgJaA9DCCqqfqXzA0jAlIaUUpRoFUt6aBZHQIFOvnhbW3B1fZQoaAZoCWgPQwgs9SwI5e0ZQJSGlFKUaBVLlWgWR0CBUQxGlQ/HdX2UKGgGaAloD0MImpSCbi/p8j+UhpRSlGgVS4BoFkdAgVE8UuctoXV9lChoBmgJaA9DCPDbEOM1dzpAlIaUUpRoFUuNaBZHQIFSBS1maph1fZQoaAZoCWgPQwi858ByhPRawJSGlFKUaBVLYmgWR0CBUvIClrM1dX2UKGgGaAloD0MIXHNH/8t9QMCUhpRSlGgVS8RoFkdAgVOjW07bL3V9lChoBmgJaA9DCPJEEOfhBEVAlIaUUpRoFUuraBZHQIFT0EvCdjJ1fZQoaAZoCWgPQwisVFBR9bcwwJSGlFKUaBVLkWgWR0CBVFbjcVQAdX2UKGgGaAloD0MISN45lKFaFsCUhpRSlGgVS4toFkdAgVTcEFGG23V9lChoBmgJaA9DCGJmn8cowzRAlIaUUpRoFUubaBZHQIFWBPbfxc51fZQoaAZoCWgPQwiLNse5TXgOwJSGlFKUaBVLq2gWR0CBWQBMBZIQdX2UKGgGaAloD0MIgZauYBvVMMCUhpRSlGgVS7NoFkdAgVppVsDW9XV9lChoBmgJaA9DCLXgRV9B2kRAlIaUUpRoFU3oA2gWR0CBWufcvduYdX2UKGgGaAloD0MId78K8N2mKcCUhpRSlGgVS3hoFkdAgVuvddmg8XV9lChoBmgJaA9DCMwpATEJEzzAlIaUUpRoFUvJaBZHQIFbywjdHlR1fZQoaAZoCWgPQwixMEROX88NQJSGlFKUaBVLqGgWR0CBXC9/z8P4dX2UKGgGaAloD0MI1NFxNbLbR0CUhpRSlGgVS5NoFkdAgVyrftQbdnV9lChoBmgJaA9DCLyTT49trT1AlIaUUpRoFUuvaBZHQIFcxnOB19x1fZQoaAZoCWgPQwjRBIpYxJAQQJSGlFKUaBVLl2gWR0CBXaRHPNVzdX2UKGgGaAloD0MIvFzEd2JqOsCUhpRSlGgVS5RoFkdAgV344ACGOHV9lChoBmgJaA9DCBCugEI9pTFAlIaUUpRoFUuRaBZHQIFeRUT+NtJ1fZQoaAZoCWgPQwgqO/2gLiI2wJSGlFKUaBVLwWgWR0CBXo9pRGc4dX2UKGgGaAloD0MIJSL8i6CRNsCUhpRSlGgVS4VoFkdAgWFFUhmoSHV9lChoBmgJaA9DCAg9m1WfsUBAlIaUUpRoFUvHaBZHQIFirK3d9Dx1fZQoaAZoCWgPQwilwAKYMggzQJSGlFKUaBVLbWgWR0CBYr3bmEGrdX2UKGgGaAloD0MI+FCiJY8eWsCUhpRSlGgVS4VoFkdAgWPSGBWge3V9lChoBmgJaA9DCMmRzsDIlzpAlIaUUpRoFUuPaBZHQIFljA+IM0B1fZQoaAZoCWgPQwh+AFKbOLlDwJSGlFKUaBVLimgWR0CBZmGrS3LFdX2UKGgGaAloD0MI2ZQrvMtRQ8CUhpRSlGgVS7xoFkdAgWa9Vmz0H3V9lChoBmgJaA9DCDApPj4hK0JAlIaUUpRoFUuVaBZHQIFn8IHC4z91fZQoaAZoCWgPQwhNDwpK0RhAwJSGlFKUaBVLk2gWR0CBaB8TBZZCdX2UKGgGaAloD0MIS6shcY8pVUCUhpRSlGgVTegDaBZHQIFpkPrfLs91fZQoaAZoCWgPQwhUkJ+NXC8xQJSGlFKUaBVLi2gWR0CBarP9DQZ5dX2UKGgGaAloD0MIIv/MID4IKcCUhpRSlGgVS5JoFkdAgWyiOFQEZHV9lChoBmgJaA9DCJrrNNJS+R5AlIaUUpRoFUuoaBZHQIFuOALApKB1fZQoaAZoCWgPQwjg88MI4e1aQJSGlFKUaBVN6ANoFkdAgXA7tRekYXV9lChoBmgJaA9DCFAdq5SeETTAlIaUUpRoFUubaBZHQIFwZKDkELZ1fZQoaAZoCWgPQwhKQbeXNNY0wJSGlFKUaBVLtWgWR0CBcGIwdsBRdX2UKGgGaAloD0MIBqBRuvQvvb+UhpRSlGgVS4JoFkdAgXDpGnXNDHV9lChoBmgJaA9DCGn8witJDkTAlIaUUpRoFUuEaBZHQIFzote2NNt1fZQoaAZoCWgPQwiphZLJqeUgQJSGlFKUaBVLpGgWR0CBdKjcEeQudX2UKGgGaAloD0MImSuDaoNbM0CUhpRSlGgVS4RoFkdAgXqq1XvH93V9lChoBmgJaA9DCB6mfXN/sV3AlIaUUpRoFU2xAWgWR0CBfCCEHt4SdX2UKGgGaAloD0MIKSFYVS+FQECUhpRSlGgVS59oFkdAgXxPeYUnHHV9lChoBmgJaA9DCIIclDDTAjXAlIaUUpRoFUutaBZHQIF9WsA/9pB1fZQoaAZoCWgPQwgO+PwwQudZQJSGlFKUaBVN6ANoFkdAgX7XHJcPfHV9lChoBmgJaA9DCARY5NcPBTJAlIaUUpRoFUuWaBZHQIGA/HaN+9d1fZQoaAZoCWgPQwiPpQ9dUJRewJSGlFKUaBVL/2gWR0CBgejtXxOMdX2UKGgGaAloD0MIw4AlV7FOQkCUhpRSlGgVS+BoFkdAgYXuBDohZHV9lChoBmgJaA9DCJPEknL3uRHAlIaUUpRoFUtyaBZHQIGGyjk+5e91fZQoaAZoCWgPQwjjHHV0XAEywJSGlFKUaBVLhmgWR0CBh3nrY5DJdX2UKGgGaAloD0MIWDuKc9T9NUCUhpRSlGgVS6poFkdAgYj9TxXnyXV9lChoBmgJaA9DCOEIUil25CdAlIaUUpRoFUt8aBZHQIGJGEZiuuB1fZQoaAZoCWgPQwgwStBf6GVDwJSGlFKUaBVLwWgWR0CBjIa9bor4dX2UKGgGaAloD0MIdvwXCAKiQkCUhpRSlGgVS6xoFkdAgZGthuwX7HV9lChoBmgJaA9DCApMp3Ub5DRAlIaUUpRoFUuVaBZHQIGVMBfa6Bl1fZQoaAZoCWgPQwgXEjC6vENAwJSGlFKUaBVLqmgWR0CBlkj9GZuydX2UKGgGaAloD0MIdqT6zi8KC8CUhpRSlGgVS5poFkdAgZZ91dPcjHV9lChoBmgJaA9DCKzmOSLfDSjAlIaUUpRoFUuTaBZHQIGXnB7/n4h1fZQoaAZoCWgPQwi2Dg72JoboP5SGlFKUaBVLlmgWR0CBmAGVzIV/dWUu"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 52,
     "n_steps": 1024,
-    "gamma": 0.999,
+    "gamma": 0.995,
     "gae_lambda": 0.98,
     "ent_coef": 0.01,
     "vf_coef": 0.5,

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2497affac19a461e040f7a57c9a5933e93b10b5579b0a3d91d7d3978070520ec
-size 687
+oid sha256:a7a4ae07089547a04d0a1d26150b01db7e0f44eb2e9b6816c2b57b0373a57851
+size 87929

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9c2476470f6b15211f79a9d12a961f174b4ec60760ecc072a359fdcd7a3481e
+oid sha256:6d7fd408b98eba481659aaafce9b3bed4d0e2fb050c6ca261fd2f53475fa07ca
 size 43201

results.json

@@ -1 +1 @@
-{"mean_reward": -124.87026343063626, "std_reward": 34.551933355813006, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-18T15:03:37.134436"}
+{"mean_reward": -162.66703254674212, "std_reward": 61.53771506248648, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-18T16:32:09.990401"}