Another commit

PandaReachDenseSAC-n2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f83a57741b6ce95cddeddb5586c56b9866414e85cc6fbbdeb9e11ca242b8cc2
+size 2564821

PandaReachDenseSAC-n2/_stable_baselines3_version

@@ -0,0 +1 @@
+1.7.0

PandaReachDenseSAC-n2/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4a558fa706ecd287dcebb57b7da4eed85b783b107d3b09daaffa592c12daf09
+size 687

PandaReachDenseSAC-n2/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96eaf19122a570afadeadabbbd7a29ea400e2286bc189f713dabfed664043523
+size 687

PandaReachDenseSAC-n2/data

@@ -0,0 +1,96 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVNwAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnNhYy5wb2xpY2llc5SMEE11bHRpSW5wdXRQb2xpY3mUk5Qu",
+        "__module__": "stable_baselines3.sac.policies",
+        "__doc__": "\n    Policy class (with both actor and critic) for SAC.\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 use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` when using gSDE 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 clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\n    :param features_extractor_class: Features extractor to use.\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    :param n_critics: Number of critic networks to create.\n    :param share_features_extractor: Whether to share or not the features extractor\n        between the actor and the critic (this saves computation time)\n    ",
+        "__init__": "<function MultiInputPolicy.__init__ at 0x7f3458b4e670>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f3458b4dc40>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "net_arch": [
+            400,
+            300
+        ],
+        "use_sde": true
+    },
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.dict.Dict'>",
+        ":serialized:": "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",
+        "spaces": "OrderedDict([('achieved_goal', Box([-10. -10. -10.], [10. 10. 10.], (3,), float32)), ('desired_goal', Box([-10. -10. -10.], [10. 10. 10.], (3,), float32)), ('observation', Box([-10. -10. -10. -10. -10. -10.], [10. 10. 10. 10. 10. 10.], (6,), float32))])",
+        "_shape": null,
+        "dtype": null,
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "gAWVbQEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLA4WUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWDAAAAAAAAAAAAIC/AACAvwAAgL+UaApLA4WUjAFDlHSUUpSMBGhpZ2iUaBIolgwAAAAAAAAAAACAPwAAgD8AAIA/lGgKSwOFlGgVdJRSlIwNYm91bmRlZF9iZWxvd5RoEiiWAwAAAAAAAAABAQGUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLA4WUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYDAAAAAAAAAAEBAZRoIUsDhZRoFXSUUpSMCl9ucF9yYW5kb22UTnViLg==",
+        "dtype": "float32",
+        "_shape": [
+            3
+        ],
+        "low": "[-1. -1. -1.]",
+        "high": "[1. 1. 1.]",
+        "bounded_below": "[ True  True  True]",
+        "bounded_above": "[ True  True  True]",
+        "_np_random": null
+    },
+    "n_envs": 1,
+    "num_timesteps": 0,
+    "_total_timesteps": 0,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": null,
+    "learning_rate": 0.0008,
+    "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": true,
+    "sde_sample_freq": 8,
+    "_current_progress_remaining": 1,
+    "ep_info_buffer": null,
+    "ep_success_buffer": null,
+    "_n_updates": 0,
+    "buffer_size": 300000,
+    "batch_size": 256,
+    "learning_starts": 10000,
+    "tau": 0.005,
+    "gamma": 0.99,
+    "gradient_steps": 1,
+    "optimize_memory_usage": false,
+    "replay_buffer_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVOQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwQRGljdFJlcGxheUJ1ZmZlcpSTlC4=",
+        "__module__": "stable_baselines3.common.buffers",
+        "__doc__": "\n    Dict Replay buffer used in off-policy algorithms like SAC/TD3.\n    Extends the ReplayBuffer to use dictionary observations\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param n_envs: Number of parallel environments\n    :param optimize_memory_usage: Enable a memory efficient variant\n        Disabled for now (see https://github.com/DLR-RM/stable-baselines3/pull/243#discussion_r531535702)\n    :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n        separately and treat the task as infinite horizon task.\n        https://github.com/DLR-RM/stable-baselines3/issues/284\n    ",
+        "__init__": "<function DictReplayBuffer.__init__ at 0x7f3458b9a430>",
+        "add": "<function DictReplayBuffer.add at 0x7f3458b9a4c0>",
+        "sample": "<function DictReplayBuffer.sample at 0x7f3458b9a550>",
+        "_get_samples": "<function DictReplayBuffer._get_samples at 0x7f3458b9a5e0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f3458b94e00>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "target_entropy": {
+        ":type:": "<class 'numpy.float32'>",
+        ":serialized:": "gAWVZQAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMEAABAwJSGlFKULg=="
+    },
+    "ent_coef": "auto",
+    "target_update_interval": 1,
+    "batch_norm_stats": [],
+    "batch_norm_stats_target": []
+}

PandaReachDenseSAC-n2/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:584db50b2c187ebf1e086b7472b04f4e059c907f7852f8146e9773c1619dfc1f
+size 687

PandaReachDenseSAC-n2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cda1cf443e0746e7cd6959ca8d31167cf6b20d1a6167468e87dcb29ed98e9756
+size 2552264

PandaReachDenseSAC-n2/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13c30a0c9369287fb864c476a977e5d54153e3d2ed91f5a395a046c55a406fdb
+size 747

PandaReachDenseSAC-n2/system_info.txt

@@ -0,0 +1,7 @@
+- OS: Linux-5.15.0-60-generic-x86_64-with-glibc2.35 # 66-Ubuntu SMP Fri Jan 20 14:29:49 UTC 2023
+- Python: 3.9.16
+- Stable-Baselines3: 1.7.0
+- PyTorch: 1.13.1+cu117
+- GPU Enabled: True
+- Numpy: 1.21.6
+- Gym: 0.21.0

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- PandaReachDense-v2
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: SAC
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: PandaReachDense-v2
+      type: PandaReachDense-v2
+    metrics:
+    - type: mean_reward
+      value: -10.07 +/- 2.92
+      name: mean_reward
+      verified: false
+---
+
+# **SAC** Agent playing **PandaReachDense-v2**
+This is a trained model of a **SAC** agent playing **PandaReachDense-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:": "gAWVNwAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnNhYy5wb2xpY2llc5SMEE11bHRpSW5wdXRQb2xpY3mUk5Qu", "__module__": "stable_baselines3.sac.policies", "__doc__": "\n    Policy class (with both actor and critic) for SAC.\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 use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` when using gSDE 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 clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\n    :param features_extractor_class: Features extractor to use.\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    :param n_critics: Number of critic networks to create.\n    :param share_features_extractor: Whether to share or not the features extractor\n        between the actor and the critic (this saves computation time)\n    ", "__init__": "<function MultiInputPolicy.__init__ at 0x7f3458b4e670>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f3458b4dc40>"}, "verbose": 1, "policy_kwargs": {"net_arch": [400, 300], "use_sde": true}, "observation_space": {":type:": "<class 'gym.spaces.dict.Dict'>", ":serialized:": "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", "spaces": "OrderedDict([('achieved_goal', Box([-10. -10. -10.], [10. 10. 10.], (3,), float32)), ('desired_goal', Box([-10. -10. -10.], [10. 10. 10.], (3,), float32)), ('observation', Box([-10. -10. -10. -10. -10. -10.], [10. 10. 10. 10. 10. 10.], (6,), float32))])", "_shape": null, "dtype": null, "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [3], "low": "[-1. -1. -1.]", "high": "[1. 1. 1.]", "bounded_below": "[ True  True  True]", "bounded_above": "[ True  True  True]", "_np_random": null}, "n_envs": 1, "num_timesteps": 0, "_total_timesteps": 0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": null, "learning_rate": 0.0008, "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": true, "sde_sample_freq": 8, "_current_progress_remaining": 1, "ep_info_buffer": null, "ep_success_buffer": null, "_n_updates": 0, "buffer_size": 300000, "batch_size": 256, "learning_starts": 10000, "tau": 0.005, "gamma": 0.99, "gradient_steps": 1, "optimize_memory_usage": false, "replay_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwQRGljdFJlcGxheUJ1ZmZlcpSTlC4=", "__module__": "stable_baselines3.common.buffers", "__doc__": "\n    Dict Replay buffer used in off-policy algorithms like SAC/TD3.\n    Extends the ReplayBuffer to use dictionary observations\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param n_envs: Number of parallel environments\n    :param optimize_memory_usage: Enable a memory efficient variant\n        Disabled for now (see https://github.com/DLR-RM/stable-baselines3/pull/243#discussion_r531535702)\n    :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n        separately and treat the task as infinite horizon task.\n        https://github.com/DLR-RM/stable-baselines3/issues/284\n    ", "__init__": "<function DictReplayBuffer.__init__ at 0x7f3458b9a430>", "add": "<function DictReplayBuffer.add at 0x7f3458b9a4c0>", "sample": "<function DictReplayBuffer.sample at 0x7f3458b9a550>", "_get_samples": "<function DictReplayBuffer._get_samples at 0x7f3458b9a5e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f3458b94e00>"}, "replay_buffer_kwargs": {}, "train_freq": {":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>", ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"}, "use_sde_at_warmup": false, "target_entropy": {":type:": "<class 'numpy.float32'>", ":serialized:": "gAWVZQAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMEAABAwJSGlFKULg=="}, "ent_coef": "auto", "target_update_interval": 1, "batch_norm_stats": [], "batch_norm_stats_target": [], "system_info": {"OS": "Linux-5.15.0-60-generic-x86_64-with-glibc2.35 # 66-Ubuntu SMP Fri Jan 20 14:29:49 UTC 2023", "Python": "3.9.16", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu117", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}

results.json

@@ -0,0 +1 @@
+{"mean_reward": -10.067005313187838, "std_reward": 2.918267742484218, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-17T15:21:10.008032"}

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:102e566432ced69f7d52d86780cdcbd9dda3a18fe4ad56f951ecf0133cf5b835
+size 3056