Retrain PPO model for FrozenLake-v1 v0

.gitattributes

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.mp4 filter=lfs diff=lfs merge=lfs -text

PPO-FrozenLake-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9d646c110e268876753ce1eaa7e7fd050c072e7cc7afbc9db1f88159719d3fb
+size 40534

PPO-FrozenLake-v1/_stable_baselines3_version

@@ -0,0 +1 @@
+1.5.0

PPO-FrozenLake-v1/data

@@ -0,0 +1,109 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
+        "__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 0x7f6f7e96a5f0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f6f7e96a680>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f6f7e96a710>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f6f7e96a7a0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f6f7e96a830>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f6f7e96a8c0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f6f7e96a950>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f6f7e96a9e0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f6f7e96aa70>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f6f7e96ab00>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f6f7e96ab90>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f6f7e9aede0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        ":type:": "<class 'dict'>",
+        ":serialized:": "gASVbAAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARTRUxVlJOUjAhuZXRfYXJjaJRdlH2UKIwCcGmUXZQoSwxLDEsMZYwCdmaUXZQoSwxLDEsMZXVhdS4=",
+        "activation_fn": "<class 'torch.nn.modules.activation.SELU'>",
+        "net_arch": [
+            {
+                "pi": [
+                    12,
+                    12,
+                    12
+                ],
+                "vf": [
+                    12,
+                    12,
+                    12
+                ]
+            }
+        ]
+    },
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
+        ":serialized:": "gASVjAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLEIwFc3RhcnSUSwCMBl9zaGFwZZQpjAVkdHlwZZSMBW51bXB5lGgIk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMCl9ucF9yYW5kb22UTnViLg==",
+        "n": 16,
+        "start": 0,
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
+        ":serialized:": "gASVjAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwFc3RhcnSUSwCMBl9zaGFwZZQpjAVkdHlwZZSMBW51bXB5lGgIk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMCl9ucF9yYW5kb22UTnViLg==",
+        "n": 4,
+        "start": 0,
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 16,
+    "num_timesteps": 106496,
+    "_total_timesteps": 100000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1652278560.8929634,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "gASVvwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxIL29wdC9jb25kYS9saWIvcHl0aG9uMy43L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxIL29wdC9jb25kYS9saWIvcHl0aG9uMy43L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
+    },
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASVCAEAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYolDgAQAAAAAAAAACAAAAAAAAAAEAAAAAAAAAAkAAAAAAAAACQAAAAAAAAAIAAAAAAAAAAAAAAAAAAAADQAAAAAAAAAAAAAAAAAAAA0AAAAAAAAAAAAAAAAAAAAEAAAAAAAAAAQAAAAAAAAACgAAAAAAAAAEAAAAAAAAAAAAAAAAAAAAlHSUYi4="
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="
+    },
+    "_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:": "gASV4AsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHP/AAAAAAAACMAWyUSwqMAXSUR0CQQ973wkPddX2UKGgGRz/wAAAAAAAAaAdLG2gIR0CQQ+SdvsJIdX2UKGgGRz/wAAAAAAAAaAdLGmgIR0CQQ9zv7WNFdX2UKGgGRz/wAAAAAAAAaAdLJGgIR0CQQ+wl0HQhdX2UKGgGRz/wAAAAAAAAaAdLMWgIR0CQQ+zdk8RudX2UKGgGRz/wAAAAAAAAaAdLHGgIR0CQQ/FRYRukdX2UKGgGRz/wAAAAAAAAaAdLFmgIR0CQQ/BiCrcTdX2UKGgGRwAAAAAAAAAAaAdLZGgIR0CQQ+qUNayKdX2UKGgGRz/wAAAAAAAAaAdLC2gIR0CQQ+6l+EytdX2UKGgGRz/wAAAAAAAAaAdLCWgIR0CQQ+2fTTfBdX2UKGgGRwAAAAAAAAAAaAdLFGgIR0CQQ/E12q1gdX2UKGgGRz/wAAAAAAAAaAdLFWgIR0CQQ/ujASFodX2UKGgGRwAAAAAAAAAAaAdLCmgIR0CQQ/Tho/RmdX2UKGgGRz/wAAAAAAAAaAdLMmgIR0CQQ+3w1BMSdX2UKGgGRwAAAAAAAAAAaAdLK2gIR0CQRAdkJ8fFdX2UKGgGRz/wAAAAAAAAaAdLCmgIR0CQQ/qZML4OdX2UKGgGRz/wAAAAAAAAaAdLDGgIR0CQRAOp84PxdX2UKGgGRz/wAAAAAAAAaAdLHGgIR0CQRAalUIcBdX2UKGgGRwAAAAAAAAAAaAdLD2gIR0CQRAU5uIhydX2UKGgGRz/wAAAAAAAAaAdLFmgIR0CQRBTBqKxcdX2UKGgGRz/wAAAAAAAAaAdLHmgIR0CQRAzSkTHsdX2UKGgGRz/wAAAAAAAAaAdLFWgIR0CQRBzru6VddX2UKGgGRz/wAAAAAAAAaAdLF2gIR0CQRBWkJrtWdX2UKGgGRwAAAAAAAAAAaAdLIGgIR0CQRB/vfCQ+dX2UKGgGRz/wAAAAAAAAaAdLKWgIR0CQRBsoDxLCdX2UKGgGRz/wAAAAAAAAaAdLCWgIR0CQRCs189fUdX2UKGgGRz/wAAAAAAAAaAdLJ2gIR0CQRCplBhQWdX2UKGgGRwAAAAAAAAAAaAdLC2gIR0CQRB5XU6PsdX2UKGgGRz/wAAAAAAAAaAdLRmgIR0CQRC21D0DmdX2UKGgGRz/wAAAAAAAAaAdLB2gIR0CQRCkbgjyGdX2UKGgGRz/wAAAAAAAAaAdLFmgIR0CQRDdK/VRUdX2UKGgGRz/wAAAAAAAAaAdLJ2gIR0CQRDJlJ6IFdX2UKGgGRwAAAAAAAAAAaAdLC2gIR0CQRDuBczIndX2UKGgGRwAAAAAAAAAAaAdLBWgIR0CQRDEOiFj/dX2UKGgGRz/wAAAAAAAAaAdLJmgIR0CQRDbOeJ53dX2UKGgGRwAAAAAAAAAAaAdLLmgIR0CQRDZzgdfcdX2UKGgGRz/wAAAAAAAAaAdLJmgIR0CQREKIBRyfdX2UKGgGRz/wAAAAAAAAaAdLG2gIR0CQREot+TePdX2UKGgGRz/wAAAAAAAAaAdLLmgIR0CQRE/9YOlPdX2UKGgGRz/wAAAAAAAAaAdLDmgIR0CQREahpQDWdX2UKGgGRz/wAAAAAAAAaAdLE2gIR0CQRE/pMYdidX2UKGgGRz/wAAAAAAAAaAdLIGgIR0CQRFzWwu/UdX2UKGgGRwAAAAAAAAAAaAdLKWgIR0CQRFWLgn+idX2UKGgGRz/wAAAAAAAAaAdLI2gIR0CQRFGD+R5kdX2UKGgGRwAAAAAAAAAAaAdLOmgIR0CQRF60IC2ddX2UKGgGRz/wAAAAAAAAaAdLEGgIR0CQRGiyY5T7dX2UKGgGRz/wAAAAAAAAaAdLDGgIR0CQRHFI/Z/TdX2UKGgGRz/wAAAAAAAAaAdLH2gIR0CQRH/c32mIdX2UKGgGRz/wAAAAAAAAaAdLMWgIR0CQRIda+vhZdX2UKGgGRz/wAAAAAAAAaAdLIGgIR0CQRIcYIjW1dX2UKGgGRz/wAAAAAAAAaAdLLGgIR0CQRI5IYm9hdX2UKGgGRz/wAAAAAAAAaAdLIWgIR0CQRISjQAuJdX2UKGgGRwAAAAAAAAAAaAdLZGgIR0CQRIrYoRZmdX2UKGgGRz/wAAAAAAAAaAdLV2gIR0CQRI1a4c3mdX2UKGgGRz/wAAAAAAAAaAdLN2gIR0CQRIwNLDhtdX2UKGgGRz/wAAAAAAAAaAdLIWgIR0CQRJxbSqlxdX2UKGgGRz/wAAAAAAAAaAdLQmgIR0CQRJ4zabnYdX2UKGgGRz/wAAAAAAAAaAdLLGgIR0CQRKGxUvPDdX2UKGgGRz/wAAAAAAAAaAdLH2gIR0CQRKH2AXl9dX2UKGgGRz/wAAAAAAAAaAdLPGgIR0CQRKAX2ugZdX2UKGgGRz/wAAAAAAAAaAdLOGgIR0CQRJ37DVH4dX2UKGgGRz/wAAAAAAAAaAdLDGgIR0CQRK8FINExdX2UKGgGRz/wAAAAAAAAaAdLT2gIR0CQRKjFAE+xdX2UKGgGRwAAAAAAAAAAaAdLEGgIR0CQRKRA8jiXdX2UKGgGRz/wAAAAAAAAaAdLFWgIR0CQRK+A3DNydX2UKGgGRz/wAAAAAAAAaAdLEWgIR0CQRKfiPyTZdX2UKGgGRwAAAAAAAAAAaAdLS2gIR0CQRKuTRplCdX2UKGgGRwAAAAAAAAAAaAdLCmgIR0CQRK2Dxsl+dX2UKGgGRz/wAAAAAAAAaAdLCmgIR0CQRL6tknTidX2UKGgGRz/wAAAAAAAAaAdLB2gIR0CQRLaF23a0dX2UKGgGRz/wAAAAAAAAaAdLGWgIR0CQRMUVBUrDdX2UKGgGRz/wAAAAAAAAaAdLDWgIR0CQRMO9WZJDdX2UKGgGRz/wAAAAAAAAaAdLGWgIR0CQRMiLEUCadX2UKGgGRz/wAAAAAAAAaAdLC2gIR0CQRM+xW1c/dX2UKGgGRz/wAAAAAAAAaAdLImgIR0CQRMD6WPcSdX2UKGgGRz/wAAAAAAAAaAdLDmgIR0CQRMNQj2SMdX2UKGgGRwAAAAAAAAAAaAdLGGgIR0CQRM0eU6gedX2UKGgGRz/wAAAAAAAAaAdLHGgIR0CQRM/GEPDpdX2UKGgGRz/wAAAAAAAAaAdLLmgIR0CQRMy2QXANdX2UKGgGRz/wAAAAAAAAaAdLJWgIR0CQRNmvnr6ddX2UKGgGRz/wAAAAAAAAaAdLJGgIR0CQRODHOryUdX2UKGgGRz/wAAAAAAAAaAdLQWgIR0CQRO3mFJxvdX2UKGgGRwAAAAAAAAAAaAdLLmgIR0CQROpzcRDkdX2UKGgGRwAAAAAAAAAAaAdLPWgIR0CQROe7L+xXdX2UKGgGRz/wAAAAAAAAaAdLD2gIR0CQROV9F4LUdX2UKGgGRz/wAAAAAAAAaAdLFWgIR0CQROW9lEqldX2UKGgGRz/wAAAAAAAAaAdLRmgIR0CQRO87ZFoddX2UKGgGRz/wAAAAAAAAaAdLIGgIR0CQRP0OEug6dX2UKGgGRz/wAAAAAAAAaAdLD2gIR0CQRQUbDMvAdX2UKGgGRz/wAAAAAAAAaAdLDmgIR0CQRQCgbp/xdX2UKGgGRz/wAAAAAAAAaAdLGGgIR0CQRQtT1kDqdX2UKGgGRz/wAAAAAAAAaAdLLmgIR0CQRRJUYKpldX2UKGgGRz/wAAAAAAAAaAdLMGgIR0CQRRSJj2BbdX2UKGgGRz/wAAAAAAAAaAdLIGgIR0CQRRG/vfCRdX2UKGgGRz/wAAAAAAAAaAdLE2gIR0CQRR6lLvkSdX2UKGgGRz/wAAAAAAAAaAdLHGgIR0CQRR+H8CPqdX2UKGgGRz/wAAAAAAAAaAdLMmgIR0CQRRYsd1dPdX2UKGgGRwAAAAAAAAAAaAdLDGgIR0CQRSBiTdLydX2UKGgGRwAAAAAAAAAAaAdLNGgIR0CQRShpQDV6dX2UKGgGRwAAAAAAAAAAaAdLPWgIR0CQRR127nPndWUu"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 200,
+    "n_steps": 512,
+    "gamma": 0.97,
+    "gae_lambda": 0.98,
+    "ent_coef": 0.01,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "batch_size": 32,
+    "n_epochs": 4,
+    "clip_range": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null
+}

PPO-FrozenLake-v1/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49f31674be06be8dfca70c1eaab6d4c413590699b15cbf3f16ae5c636db4ae6d
+size 16965

PPO-FrozenLake-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0825af843602f21aa310dc9ef1715468b6f023835dff8b060a8e0d3d273a4096
+size 9589

PPO-FrozenLake-v1/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
+size 431

PPO-FrozenLake-v1/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.10.107+-x86_64-with-debian-bullseye-sid #1 SMP Sun Apr 24 15:04:08 UTC 2022
+Python: 3.7.12
+Stable-Baselines3: 1.5.0
+PyTorch: 1.9.1
+GPU Enabled: True
+Numpy: 1.21.6
+Gym: 0.23.1

README.md

@@ -0,0 +1,28 @@
+---
+library_name: stable-baselines3
+tags:
+- FrozenLake-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 0.80 +/- 0.40
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: FrozenLake-v1
+      type: FrozenLake-v1
+---
+
+  # **PPO** Agent playing **FrozenLake-v1**
+  This is a trained model of a **PPO** agent playing **FrozenLake-v1** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
+  
+  ## Usage (with Stable-baselines3)
+  TODO: Add your code
+  

config.json

@@ -0,0 +1 @@
+{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__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 0x7f6f7e96a5f0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f6f7e96a680>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f6f7e96a710>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f6f7e96a7a0>", "_build": "<function ActorCriticPolicy._build at 0x7f6f7e96a830>", "forward": "<function ActorCriticPolicy.forward at 0x7f6f7e96a8c0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f6f7e96a950>", "_predict": "<function ActorCriticPolicy._predict at 0x7f6f7e96a9e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f6f7e96aa70>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f6f7e96ab00>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f6f7e96ab90>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f6f7e9aede0>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gASVbAAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARTRUxVlJOUjAhuZXRfYXJjaJRdlH2UKIwCcGmUXZQoSwxLDEsMZYwCdmaUXZQoSwxLDEsMZXVhdS4=", "activation_fn": "<class 'torch.nn.modules.activation.SELU'>", "net_arch": [{"pi": [12, 12, 12], "vf": [12, 12, 12]}]}, "observation_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gASVjAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLEIwFc3RhcnSUSwCMBl9zaGFwZZQpjAVkdHlwZZSMBW51bXB5lGgIk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMCl9ucF9yYW5kb22UTnViLg==", "n": 16, "start": 0, "_shape": [], "dtype": "int64", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gASVjAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwFc3RhcnSUSwCMBl9zaGFwZZQpjAVkdHlwZZSMBW51bXB5lGgIk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMCl9ucF9yYW5kb22UTnViLg==", "n": 4, "start": 0, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 106496, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1652278560.8929634, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gASVvwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxIL29wdC9jb25kYS9saWIvcHl0aG9uMy43L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxIL29wdC9jb25kYS9saWIvcHl0aG9uMy43L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gASVCAEAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYolDgAQAAAAAAAAACAAAAAAAAAAEAAAAAAAAAAkAAAAAAAAACQAAAAAAAAAIAAAAAAAAAAAAAAAAAAAADQAAAAAAAAAAAAAAAAAAAA0AAAAAAAAAAAAAAAAAAAAEAAAAAAAAAAQAAAAAAAAACgAAAAAAAAAEAAAAAAAAAAAAAAAAAAAAlHSUYi4="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="}, "_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:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 200, "n_steps": 512, "gamma": 0.97, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 32, "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-5.10.107+-x86_64-with-debian-bullseye-sid #1 SMP Sun Apr 24 15:04:08 UTC 2022", "Python": "3.7.12", "Stable-Baselines3": "1.5.0", "PyTorch": "1.9.1", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.23.1"}}

results.json

@@ -0,0 +1 @@
+{"mean_reward": 0.8, "std_reward": 0.4, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-11T14:19:42.053572"}