Upload PPO LunarLander-v2 trained agent

EWS-ppo-LunarLander-v2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:920424aa08b5530e9b21cffe10133999c71c3e6e7ece5c811ddc0e7a63269462
+size 147253

EWS-ppo-LunarLander-v2/_stable_baselines3_version

@@ -0,0 +1 @@
+2.0.0a5

EWS-ppo-LunarLander-v2/data

@@ -0,0 +1,96 @@
+{
+    "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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 0x7e4fbceca320>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7e4fbceca3b0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7e4fbceca440>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7e4fbceca4d0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7e4fbceca560>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7e4fbceca5f0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7e4fbceca680>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7e4fbceca710>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7e4fbceca7a0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7e4fbceca830>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7e4fbceca8c0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7e4fbceca950>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7e4fbce6a000>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1702292193916309000,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "_last_obs": null,
+    "_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,
+    "_stats_window_size": 100,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 496,
+    "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,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True  True  True  True  True  True  True  True]",
+        "bounded_above": "[ True  True  True  True  True  True  True  True]",
+        "_shape": [
+            8
+        ],
+        "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]",
+        "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]",
+        "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]",
+        "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        "n": "4",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 16,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    }
+}

EWS-ppo-LunarLander-v2/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03876e2f934767517139dcdce00faa2f5e4379508b75932ef5b3854cdd1d406f
+size 88490

EWS-ppo-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0835414402b78b2ae8d96f6eaca2ab0d6743ccde8f3cf5729fbad0b879e22f03
+size 43762

EWS-ppo-LunarLander-v2/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
+size 864

EWS-ppo-LunarLander-v2/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023
+- Python: 3.10.12
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.1.0+cu121
+- GPU Enabled: True
+- Numpy: 1.25.2
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.25.2

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- LunarLander-v2
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: LunarLander-v2
+      type: LunarLander-v2
+    metrics:
+    - type: mean_reward
+      value: 284.86 +/- 19.86
+      name: mean_reward
+      verified: false
+---
+
+# **PPO** Agent playing **LunarLander-v2**
+This is a trained model of a **PPO** agent playing **LunarLander-v2**
+using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
+
+## Usage (with Stable-baselines3)
+TODO: Add your code
+
+
+```python
+from stable_baselines3 import ...
+from huggingface_sb3 import load_from_hub
+
+...
+```

config.json

@@ -0,0 +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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 0x7e4fbceca320>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7e4fbceca3b0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7e4fbceca440>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7e4fbceca4d0>", "_build": "<function ActorCriticPolicy._build at 0x7e4fbceca560>", "forward": "<function ActorCriticPolicy.forward at 0x7e4fbceca5f0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7e4fbceca680>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7e4fbceca710>", "_predict": "<function ActorCriticPolicy._predict at 0x7e4fbceca7a0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7e4fbceca830>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7e4fbceca8c0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7e4fbceca950>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7e4fbce6a000>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1702292193916309000, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": null, "_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, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVCwwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQHFHWOuJUHaMAWyUTRMBjAF0lEdAmF+YL5RCQnV9lChoBkdAczbcGkep42gHS/1oCEdAmF+troGIK3V9lChoBkdAcTEJhOP/72gHS/loCEdAmF/HpKSPl3V9lChoBkdAbrLvc8DB/WgHS85oCEdAmF/LSeAd4nV9lChoBkdAcK1dkauOj2gHS/1oCEdAmGARDst03nV9lChoBkdAby2WjXWe6WgHTRkBaAhHQJhggK3NLUV1fZQoaAZHQHPFTKoybhFoB00aAWgIR0CYYIVtoBaLdX2UKGgGR0Bwsr3i704BaAdL62gIR0CYYJYVIqb0dX2UKGgGR0BvfiDAaef7aAdNGwFoCEdAmGCydat9yHV9lChoBkdAbtAqn3ta6mgHS/xoCEdAmGC3TZxrBXV9lChoBkdAbxjK7qY7aWgHS/toCEdAmGC4tYjjaXV9lChoBkdAcKH8UmD15GgHTUYBaAhHQJhgvposZpB1fZQoaAZHQHAdqk2xY7toB01oAWgIR0CYYVEXtShrdX2UKGgGR0BxP+BoVVPvaAdNEAFoCEdAmGFqVhTfi3V9lChoBkdAcXz8iOearmgHS+ZoCEdAmGJGecx0uHV9lChoBkdAcrUyKvV3EGgHS/FoCEdAmGJnbM5fdHV9lChoBkdAc5hM10knkWgHS9xoCEdAmGJu6Zpi7XV9lChoBkdAb98LqlgtvmgHS+doCEdAmGKAYgq3E3V9lChoBkdAcNlMGX5WR2gHTQkBaAhHQJhi5ga3qiZ1fZQoaAZHQHJTocR15jZoB0vyaAhHQJhi9br1M/R1fZQoaAZHQHHMMtK7I1doB0vZaAhHQJhjOvHLidd1fZQoaAZHQHGqPD+BH09oB00eAWgIR0CYY1fra/RFdX2UKGgGR0Bx1dsabWmQaAdL5mgIR0CYY24eLehxdX2UKGgGR0BxtDo1UEPlaAdL9WgIR0CYY21zQu27dX2UKGgGR0BwK/x+az/qaAdL8WgIR0CYY29uxbB5dX2UKGgGR0A+wjZ+QU5/aAdLYGgIR0CYY5JiiItUdX2UKGgGR0BwaIIhQm/naAdNDwFoCEdAmGPr2L5yl3V9lChoBkdAclBgE2YOUmgHTSUBaAhHQJhj9AD7qIJ1fZQoaAZHQHIOCcG1QZZoB00tAWgIR0CYZDXD3ueCdX2UKGgGR0BuFFMsYl6aaAdNEgFoCEdAmGSkyk9EC3V9lChoBkdAcb2TFVDKHWgHTQ4BaAhHQJhktVuJk5J1fZQoaAZHQHLs0ILPUrloB00HAWgIR0CYZb7sv7FbdX2UKGgGR0BUIjoIOYplaAdLgmgIR0CYZelS0jTsdX2UKGgGR0BxTxVaOgg6aAdL6GgIR0CYZeygPEsKdX2UKGgGR0BUdi/GlyimaAdLvWgIR0CYZfglWwNcdX2UKGgGR0BvsugpSaVlaAdNEgFoCEdAmGX5LRKHwnV9lChoBkdAcABtmcvugGgHTRMBaAhHQJhmD0XgtOF1fZQoaAZHQHFJxrN4Z/FoB00KAWgIR0CYapEl3QlbdX2UKGgGR0BwyECOmzjWaAdL72gIR0CYarAP/aQFdX2UKGgGR0By8RVPva11aAdL+GgIR0CYarjMV1wHdX2UKGgGR0BwC/Vd5Y5laAdNAAFoCEdAmGrmcriEQHV9lChoBkdAcQ8XBP9DQmgHTQcBaAhHQJhq/In0Cih1fZQoaAZHQHMGUqH446xoB00qAWgIR0CYaz0EHMUzdX2UKGgGR0BxKNxgiNbUaAdL72gIR0CYazmQr+YMdX2UKGgGR0By7WARTS9eaAdNBgFoCEdAmGt9+PRzBHV9lChoBkdAcba01IiC8WgHS/hoCEdAmGwKSPluFnV9lChoBkdAVFTSv1UVBWgHS59oCEdAmGydALRa5nV9lChoBkdAcXApCrtE5WgHTSwBaAhHQJhs2InBtUJ1fZQoaAZHQHCsNVea8YhoB0vjaAhHQJhtMUL2HtZ1fZQoaAZHQHLBIQrc0tRoB0vwaAhHQJhtTKkl/pd1fZQoaAZHQHBW8QNCqp9oB0v+aAhHQJhtdFgDzRR1fZQoaAZHQHMNT7l7tzFoB00MAWgIR0CYbbcW0qpcdX2UKGgGR0Bxff3TNMXaaAdL7GgIR0CYbdNqQA+7dX2UKGgGR0BwR9g6U7jlaAdL/GgIR0CYbd8nuy/sdX2UKGgGR0BxmJepn6EbaAdNJAFoCEdAmG4By0a6z3V9lChoBkdAb+d0tAcDKmgHS91oCEdAmG4vFrEcbXV9lChoBkdAcIPSlWOp9GgHS/doCEdAmG49y5qdpnV9lChoBkdAbT+coYvWYmgHTQEBaAhHQJhuRvJiiIt1fZQoaAZHQHE5DDKoybhoB0v6aAhHQJhuwj8k2P11fZQoaAZHQHK0YGt6ol5oB00cAWgIR0CYbtlNUOurdX2UKGgGR0BzJEnx8UmEaAdL32gIR0CYb3cGTs6adX2UKGgGR0BxWrJeVs1saAdNDAFoCEdAmG98/lhgE3V9lChoBkdAcM6Cm/FirmgHS+1oCEdAmG/TuF6Av3V9lChoBkdActokCFK02WgHS+FoCEdAmHAR6a9bo3V9lChoBkdAcYFbBGhEjWgHTQgBaAhHQJhwiAavRqp1fZQoaAZHQHJq3Zf2K2toB0vgaAhHQJhwndIoVmB1fZQoaAZHQEVhcbBGhEloB0vJaAhHQJhwot5D7ZZ1fZQoaAZHQHCuotthuwZoB0vxaAhHQJhwz8Muvll1fZQoaAZHQHBiaYZ2pyZoB0vvaAhHQJhxRLL6k691fZQoaAZHQHGqHztkWh1oB00sAWgIR0CYcVKzRhMKdX2UKGgGR0BwDffqHGjsaAdNBAFoCEdAmHFNa+vhZXV9lChoBkdAb0babF0gbWgHTSQBaAhHQJhxb+cYqG11fZQoaAZHQHFs5H7P6bhoB00kAWgIR0CYcfSHuZ1FdX2UKGgGR0BwnFTP0I1MaAdL/mgIR0CYcgvvjOs1dX2UKGgGR0BywwKBun/DaAdNAwFoCEdAmHI1Jg9eQnV9lChoBkdAbyhglWwNb2gHS/FoCEdAmHKood+5OXV9lChoBkdAbu/jABT4tmgHTQQBaAhHQJhy793r2QJ1fZQoaAZHQHIYUFW4mTloB0vyaAhHQJhzDxpcoph1fZQoaAZHQFIK3c580DVoB0udaAhHQJhzP238XN11fZQoaAZHQHAR7YoRZlpoB00JAWgIR0CYc5iKiwjddX2UKGgGR0BzFAYsNDtxaAdL4mgIR0CYc8O+IuXedX2UKGgGR0BwBpGnXNC7aAdL+2gIR0CYc+o1DSgHdX2UKGgGR0BzeK1RceKbaAdLzWgIR0CYc+pJPIn0dX2UKGgGR0BvA331zySWaAdNCgFoCEdAmHQGeg+Ql3V9lChoBkdAciEuoxYaHmgHTRcBaAhHQJh0PvkRzzV1fZQoaAZHQHNKOLR8c+9oB0v5aAhHQJh0bxUedTZ1fZQoaAZHQHKM9q+JxedoB0v6aAhHQJh0jwvxpcp1fZQoaAZHQHHo0n5SFXdoB0v6aAhHQJh1GrFOwgV1fZQoaAZHQHCOkz9CNS9oB0v2aAhHQJh1Jb2USqV1fZQoaAZHQHCw/llsguBoB0v0aAhHQJh1SqKgqVh1fZQoaAZHQHHf/ZAY51hoB0vXaAhHQJh1Xzf779B1fZQoaAZHQG9O5BC2MKloB00SAWgIR0CYdn8Q7LdOdX2UKGgGR0BvvJXuE25yaAdL42gIR0CYdox+rlvIdX2UKGgGR0BwW8JfICEIaAdNCgFoCEdAmHbBGx2SuHV9lChoBkdAcJD5lvqC6GgHTSYBaAhHQJh2+Ad4mkZ1fZQoaAZHQGTW+XRgJC1oB03oA2gIR0CYdwaESM99dX2UKGgGR0ByFXWUbDMvaAdL+mgIR0CYdxlY2bXpdX2UKGgGR0Bx65o24uscaAdL8mgIR0CYd0Kmbb1zdX2UKGgGR0BwWlCJGe+VaAdL4GgIR0CYd31Bt1p1dX2UKGgGR0BwgGYG+sYEaAdNDAFoCEdAmHd3RXwLE3VlLg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 496, "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, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_shape": [8], "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

results.json

@@ -0,0 +1 @@
+{"mean_reward": 284.8558530042603, "std_reward": 19.860274699343986, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-23T01:57:47.838898"}