Test commit

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: -885.09 +/- 0.00
+      value: -915.02 +/- 0.00
       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 0x7f7e230443a0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f7e23044430>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f7e230444c0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f7e23044550>", "_build": "<function ActorCriticPolicy._build at 0x7f7e230445e0>", "forward": "<function ActorCriticPolicy.forward at 0x7f7e23044670>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f7e23044700>", "_predict": "<function ActorCriticPolicy._predict at 0x7f7e23044790>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f7e23044820>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f7e230448b0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f7e23044940>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f7e2303d960>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "gAWVngEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBXNoYXBllEsIhZSMA2xvd5SMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/lGgKSwiFlIwBQ5R0lFKUjARoaWdolGgSKJYgAAAAAAAAAAAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/lGgKSwiFlGgVdJRSlIwNYm91bmRlZF9iZWxvd5RoEiiWCAAAAAAAAAAAAAAAAAAAAJRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZRoFXSUUpSMDWJvdW5kZWRfYWJvdmWUaBIolggAAAAAAAAAAAAAAAAAAACUaCFLCIWUaBV0lFKUjApfbnBfcmFuZG9tlE51Yi4=", "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:": "gAWVgQAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwFc2hhcGWUKYwFZHR5cGWUjAVudW1weZRoB5OUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijApfbnBfcmFuZG9tlE51Yi4=", "n": 4, "shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "num_timesteps": 2048, "_total_timesteps": 10, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1657182692.1537936, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAKox2z4gq6c/cr+kP961yr4wzJW/daYVvwAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -203.8, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 10, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "target_kl": null, "system_info": {"OS": "Linux-5.13.0-52-generic-x86_64-with-glibc2.17 #59~20.04.1-Ubuntu SMP Thu Jun 16 21:21:28 UTC 2022", "Python": "3.8.13", "Stable-Baselines3": "1.4.0", "PyTorch": "1.12.0+cu102", "GPU Enabled": "True", "Numpy": "1.23.0", "Gym": "0.19.0"}}
+{"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 0x7f023ec0b3a0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f023ec0b430>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f023ec0b4c0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f023ec0b550>", "_build": "<function ActorCriticPolicy._build at 0x7f023ec0b5e0>", "forward": "<function ActorCriticPolicy.forward at 0x7f023ec0b670>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f023ec0b700>", "_predict": "<function ActorCriticPolicy._predict at 0x7f023ec0b790>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f023ec0b820>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f023ec0b8b0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f023ec0b940>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f023ec749c0>"}, "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:": "gAWVgQAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwFc2hhcGWUKYwFZHR5cGWUjAVudW1weZRoB5OUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijApfbnBfcmFuZG9tlE51Yi4=", "n": 4, "shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "num_timesteps": 2048, "_total_timesteps": 10, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1657182983.0519786, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVhgIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAEsBSwFLE0MEiABTAJROhZQpjAFflIWUjFYvaG9tZS9vc2Fuc2V2aWVyby8ubG9jYWwvbGliL3B5dGhvbjMuOC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4BDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5RoDXVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAKZ1Nb7CZZQ/+v0tv81JIb/4koA+ANSAPgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -203.8, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWV7QMAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMImu/gJw6gE8CUhpRSlIwBbJRLcYwBdJRHP6VSwW3z+WJ1fZQoaAZoCWgPQwjMlxdgH6BewJSGlFKUaBVLUWgWRz+xfAsTWXkYdX2UKGgGaAloD0MIXaPlQA+OWMCUhpRSlGgVS1poFkc/uUN8VpKzzHV9lChoBmgJaA9DCAwEATL0imPAlIaUUpRoFUtOaBZHP7+/gzguRLd1fZQoaAZoCWgPQwieYtUgzP5pwJSGlFKUaBVLX2gWRz/D5gw482aVdX2UKGgGaAloD0MIw0maP6bsV8CUhpRSlGgVS1VoFkc/x4vnKW9lE3V9lChoBmgJaA9DCPW6RWCsJl3AlIaUUpRoFUtzaBZHP8yBPKuB+Wp1fZQoaAZoCWgPQwgVrdwLTIphwJSGlFKUaBVLQmgWRz/PFZxJd0JXdX2UKGgGaAloD0MIt0Htt3Z1Y8CUhpRSlGgVS25oFkc/0go5PuXu3XV9lChoBmgJaA9DCBQEj29v0WTAlIaUUpRoFUtgaBZHP9P6Hj6vaDh1fZQoaAZoCWgPQwhcOXtndIFywJSGlFKUaBVLi2gWRz/XArhBJI1+dX2UKGgGaAloD0MIIZOMnIWcb8CUhpRSlGgVS2hoFkc/2SBwuM+/xnV9lChoBmgJaA9DCGNH41A/VWvAlIaUUpRoFUtUaBZHP9rbL2YfGMp1fZQoaAZoCWgPQwjRkzKpoQ1cwJSGlFKUaBVLQmgWRz/cMLWqcVgydX2UKGgGaAloD0MIdmwE4nXRWMCUhpRSlGgVS2FoFkc/3jho/RmbsnV9lChoBmgJaA9DCPhwyXFn8nbAlIaUUpRoFUtdaBZHP+AVlf7aZhN1fZQoaAZoCWgPQwgLKNTTR4BywJSGlFKUaBVLZ2gWRz/hLiEQGwA3dX2UKGgGaAloD0MIW7OVl/yIa8CUhpRSlGgVS2VoFkc/4jmEGqxTsXV9lChoBmgJaA9DCB6ILNLEYmvAlIaUUpRoFUtSaBZHP+NBSDRMN+d1fZQoaAZoCWgPQwiEDyVa8lZ2wJSGlFKUaBVLW2gWRz/kK4pc5bQkdX2UKGgGaAloD0MIycwFLo83UcCUhpRSlGgVS0doFkc/5Qp+c6Nly3V9lChoBmgJaA9DCAvtnGaBRFvAlIaUUpRoFUs8aBZHP+Wkdmxt52R1ZS4="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 10, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "target_kl": null, "system_info": {"OS": "Linux-5.13.0-52-generic-x86_64-with-glibc2.17 #59~20.04.1-Ubuntu SMP Thu Jun 16 21:21:28 UTC 2022", "Python": "3.8.13", "Stable-Baselines3": "1.4.0", "PyTorch": "1.12.0+cu102", "GPU Enabled": "True", "Numpy": "1.23.0", "Gym": "0.19.0"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7787323838d07ea15867757244f2f864d31cc1bf19f829e69635d0129c26badb
-size 141380
+oid sha256:d47c36f193a13bd6895f73344ee2dad380d33d3de025946010e737ff4673b00c
+size 141488

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 0x7f7e230443a0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f7e23044430>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f7e230444c0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f7e23044550>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f7e230445e0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f7e23044670>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f7e23044700>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f7e23044790>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f7e23044820>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f7e230448b0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f7e23044940>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f023ec0b3a0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f023ec0b430>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f023ec0b4c0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f023ec0b550>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f023ec0b5e0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f023ec0b670>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f023ec0b700>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f023ec0b790>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f023ec0b820>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f023ec0b8b0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f023ec0b940>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7f7e2303d960>"
+        "_abc_impl": "<_abc_data object at 0x7f023ec749c0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -47,7 +47,7 @@
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1657182692.1537936,
+    "start_time": 1657182983.0519786,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "lr_schedule": {
@@ -56,7 +56,7 @@
     },
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAKox2z4gq6c/cr+kP961yr4wzJW/daYVvwAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAKZ1Nb7CZZQ/+v0tv81JIb/4koA+ANSAPgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -69,7 +69,7 @@
     "_current_progress_remaining": -203.8,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6a9ac15058bdbde8519f13d4879927375a56ca3e71ef8a134bbd246772973e2
+oid sha256:4599439a86fa3f14ae344a44aeb47886e24b6a4b4f8e8c51733a49f5ae64c177
 size 87545

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79b3120047ae5a1b391f001af4884f7b9468aa98bdf0387af3eb54dece2475cb
+oid sha256:09e8a3df4978e266ece915c00e902a5246ce6ad2ad11971d6ff0609d9634f08e
 size 43073

results.json

@@ -1 +1 @@
-{"mean_reward": -885.093998, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 1, "eval_datetime": "2022-07-07T10:31:35.420053"}
+{"mean_reward": -915.021357, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 1, "eval_datetime": "2022-07-07T10:36:26.107370"}