Upload PPO LunarLander-v2 trained agent

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 163.43 +/- 33.37
+      value: 150.93 +/- 74.77
       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 0x7f56b24918c0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f56b2491950>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f56b24919e0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f56b2491a70>", "_build": "<function ActorCriticPolicy._build at 0x7f56b2491b00>", "forward": "<function ActorCriticPolicy.forward at 0x7f56b2491b90>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f56b2491c20>", "_predict": "<function ActorCriticPolicy._predict at 0x7f56b2491cb0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f56b2491d40>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f56b2491dd0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f56b2491e60>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f56b24dd810>"}, "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": 507904, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1658304625.751969, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAG2EKr777bo7adBGPKzNMLpoRlK9luYiOwAAgD8AAIA/AIG1PD0JbLstt1a87huLPHRakrw+/m49AACAPwAAgD/ukrG+uisEPhZBvj0iOXW+sT/EOxH6CD4AAAAAAAAAAIY9A76svNQ8oN0pvSSWJb6/S/W8puisvQAAAAAAAAAAc+kPv9uBJT/aJNa8hg53vh6uR72+hls9AAAAAAAAAACKSBq/splVPiB1cjzfIRa7byqGvlmQjDsAAIA/AACAP6Ocvb5PTuk+CnsnviR1c74Z71Y7b+uAvQAAAAAAAAAAAJmnPOEQlbqciIk7bVGAOIsqljp7tyS6AACAPwAAgD8z9T28w8lHunameDqatI8zEzNqusi+jrkAAIA/AACAP8YY1D79394+AicpvRCJCr5YA5E9qUG9vQAAAAAAAAAAhsYwvhKd5zwKWDa9AU4MviiSGLzdNio8AAAAAAAAAABmNds9j4Inuhp75zk8SKa1p/oDO/JqBbkAAIA/AACAP2Z+Vj2P7n66JWNYvC8ggDkqfro6DYDnuAAAgD8AAIA/zQfdPOYyuT++CbE9Vc5XvtaNV72dbeK9AAAAAAAAAADQSVO+wYaWvOYnTLvBNpG5fZMGPvZefzoAAIA/AACAPwB4Zb3pRTW84ywEux3sqzzx/aM98F+MvQAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -0.015808000000000044, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 124, "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-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.6.0", "PyTorch": "1.12.0+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 0x000002316DA511F0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000002316DA51280>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000002316DA51310>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000002316DA513A0>", "_build": "<function ActorCriticPolicy._build at 0x000002316DA51430>", "forward": "<function ActorCriticPolicy.forward at 0x000002316DA514C0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000002316DA51550>", "_predict": "<function ActorCriticPolicy._predict at 0x000002316DA515E0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000002316DA51670>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000002316DA51700>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x000002316DA51790>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x000002316DA4EBC0>"}, "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": 507904, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1658304625.751969, "learning_rate": 0.0, "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:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 124, "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": "Windows-10-10.0.19043-SP0 10.0.19043", "Python": "3.9.12", "Stable-Baselines3": "1.6.0", "PyTorch": "1.12.0+cpu", "GPU Enabled": "False", "Numpy": "1.23.1", "Gym": "0.21.0"}}

ppo-LunarLander-v2_01.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f012e43e9d28f48a0d60356d7f0fd0b95b8a959f9abf79f696a429b29613b593
-size 147139
+oid sha256:03cc9b13b2872b30f76d4eefee19aa5d7a9fe756040ca31ad8822715b1fb3a90
+size 146314

ppo-LunarLander-v2_01/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 0x7f56b24918c0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f56b2491950>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f56b24919e0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f56b2491a70>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f56b2491b00>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f56b2491b90>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f56b2491c20>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f56b2491cb0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f56b2491d40>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f56b2491dd0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f56b2491e60>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x000002316DA511F0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000002316DA51280>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000002316DA51310>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000002316DA513A0>",
+        "_build": "<function ActorCriticPolicy._build at 0x000002316DA51430>",
+        "forward": "<function ActorCriticPolicy.forward at 0x000002316DA514C0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000002316DA51550>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x000002316DA515E0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000002316DA51670>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000002316DA51700>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x000002316DA51790>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7f56b24dd810>"
+        "_abc_impl": "<_abc._abc_data object at 0x000002316DA4EBC0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -48,11 +48,11 @@
     "seed": null,
     "action_noise": null,
     "start_time": 1658304625.751969,
-    "learning_rate": 0.0003,
+    "learning_rate": 0.0,
     "tensorboard_log": null,
     "lr_schedule": {
         ":type:": "<class 'function'>",
-        ":serialized:": "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"
+        ":serialized:": "gAWVgAIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAEsBSwFLE0MEiABTAJROhZQpjAFflIWUjFBjOlxVc2Vyc1x1c2VyXC5jb25kYVxlbnZzXHJsXGxpYlxzaXRlLXBhY2thZ2VzXHN0YWJsZV9iYXNlbGluZXMzXGNvbW1vblx1dGlscy5weZSMBGZ1bmOUS4BDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5RoDXVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURwAAAAAAAAAAhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
     },
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -86,7 +86,7 @@
     "n_epochs": 4,
     "clip_range": {
         ":type:": "<class 'function'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "clip_range_vf": null,
     "normalize_advantage": true,

ppo-LunarLander-v2_01/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fee63f160b96b66d5653760f9f6b3de583767db12cc06c26d9a362303add5360
-size 87865
+oid sha256:d6afb9b9d974a12b5336262b7f9e10fefb2309c7ae69ee14c313f8daaad6ff96
+size 87545

ppo-LunarLander-v2_01/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95889af1921ee337fe712aae09dde52998fd5db6392e14a3b827f4fbe3498763
-size 43201
+oid sha256:6b65eb78b45fbd95f89f9371abe1a6c452b372ec4d5610bfe418f9230c0bdac0
+size 43073

ppo-LunarLander-v2_01/system_info.txt

@@ -1,7 +1,7 @@
-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
+OS: Windows-10-10.0.19043-SP0 10.0.19043
+Python: 3.9.12
 Stable-Baselines3: 1.6.0
-PyTorch: 1.12.0+cu113
-GPU Enabled: True
-Numpy: 1.21.6
+PyTorch: 1.12.0+cpu
+GPU Enabled: False
+Numpy: 1.23.1
 Gym: 0.21.0

results.json

@@ -1 +1 @@
-{"mean_reward": 163.43277911098883, "std_reward": 33.37182270615506, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-20T08:47:03.480876"}
+{"mean_reward": 150.9306697395636, "std_reward": 74.76521396215739, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-20T11:24:21.129274"}