SAC + HER checkpoint at 800k steps (no VecNormalize stats available)

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- PandaPickAndPlace-v3
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: SAC
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: PandaPickAndPlace-v3
+      type: PandaPickAndPlace-v3
+    metrics:
+    - type: mean_reward
+      value: -50.00 +/- 0.00
+      name: mean_reward
+      verified: false
+---
+
+# **SAC** Agent playing **PandaPickAndPlace-v3**
+This is a trained model of a **SAC** agent playing **PandaPickAndPlace-v3**
+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 0x79eaca7df4c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x79eaca7dacc0>"}, "verbose": 0, "policy_kwargs": {"use_sde": false}, "num_timesteps": 800000, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1755289801644837769, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": null, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWAQAAAAAAAAABlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksBhZSMAUOUdJRSlC4="}, "_last_original_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "gAWVYAEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwTbnVtcHkuX2NvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYMAAAAAAAAAMmOvL1xdhU9k8GjPJSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsDhpSMAUOUdJRSlIwMZGVzaXJlZF9nb2FslGgHKJYMAAAAAAAAAGvzBLzY7eK9S0TTPZRoDksBSwOGlGgSdJRSlIwLb2JzZXJ2YXRpb26UaAcolkwAAAAAAAAA6wB0PXWM6b1u5Bo+0qHmvCyXmb2LS4A+4dKjPcmOvL1xdhU9k8GjPE/GnjcfGKs2IhMIOcMe4Lfdky84xneot3x89rrnX5y6kBQPOZRoDksBSxOGlGgSdJRSlHUu", "achieved_goal": "[[-0.09206922  0.03648991  0.01998976]]", "desired_goal": "[[-0.00811468 -0.11080521  0.1031576 ]]", "observation": "[[ 5.9571188e-02 -1.1403743e-01  1.5126202e-01 -2.8153334e-02\n  -7.4995369e-02  2.5057635e-01  7.9992063e-02 -9.2069216e-02\n   3.6489908e-02  1.9989764e-02  1.8927412e-05  5.0990052e-06\n   1.2977098e-04 -2.6717205e-05  4.1860960e-05 -2.0082934e-05\n  -1.8805410e-03 -1.1930437e-03  1.3645203e-04]]"}, "_episode_num": 19431, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.20000099999999998, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVhgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKImJiYmIiYmJiYmJiYmJiYmJiYmJiIiIiYiIiYmJiImIiImJiImIiYmJiYiJiYmJiIiIiYiIiYmJiImJiYmJiImIiImJiYmJiYmIiYiIiYiJiImJiIiIiYmJiImIiIiIiYmIiYllLg=="}, "_n_updates": 799899, "observation_space": {":type:": "<class 'gymnasium.spaces.dict.Dict'>", ":serialized:": "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", "spaces": "{'achieved_goal': Box(-10.0, 10.0, (3,), float32), 'desired_goal': Box(-10.0, 10.0, (3,), float32), 'observation': Box(-10.0, 10.0, (19,), float32)}", "_shape": null, "dtype": null, "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [4], "low": "[-1. -1. -1. -1.]", "bounded_below": "[ True  True  True  True]", "high": "[1. 1. 1. 1.]", "bounded_above": "[ True  True  True  True]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": "Generator(PCG64)"}, "n_envs": 1, "buffer_size": 1000000, "batch_size": 256, "learning_starts": 100, "tau": 0.02, "gamma": 0.95, "gradient_steps": 1, "optimize_memory_usage": false, "replay_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVPwAAAAAAAACMJ3N0YWJsZV9iYXNlbGluZXMzLmhlci5oZXJfcmVwbGF5X2J1ZmZlcpSMD0hlclJlcGxheUJ1ZmZlcpSTlC4=", "__module__": "stable_baselines3.her.her_replay_buffer", "__annotations__": "{'env': typing.Optional[stable_baselines3.common.vec_env.base_vec_env.VecEnv]}", "__doc__": "\n    Hindsight Experience Replay (HER) buffer.\n    Paper: https://arxiv.org/abs/1707.01495\n\n    Replay buffer for sampling HER (Hindsight Experience Replay) transitions.\n\n    .. note::\n\n      Compared to other implementations, the ``future`` goal sampling strategy is inclusive:\n      the current transition can be used when re-sampling.\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 env: The training environment\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    :param n_sampled_goal: Number of virtual transitions to create per real transition,\n        by sampling new goals.\n    :param goal_selection_strategy: Strategy for sampling goals for replay.\n        One of ['episode', 'final', 'future']\n    :param copy_info_dict: Whether to copy the info dictionary and pass it to\n        ``compute_reward()`` method.\n        Please note that the copy may cause a slowdown.\n        False by default.\n    ", "__init__": "<function HerReplayBuffer.__init__ at 0x79eaca7bbe20>", "__getstate__": "<function HerReplayBuffer.__getstate__ at 0x79eaca7bbec0>", "__setstate__": "<function HerReplayBuffer.__setstate__ at 0x79eaca7bbf60>", "set_env": "<function HerReplayBuffer.set_env at 0x79eaca7dc040>", "add": "<function HerReplayBuffer.add at 0x79eaca7dc180>", "_compute_episode_length": "<function HerReplayBuffer._compute_episode_length at 0x79eaca7dc220>", "sample": "<function HerReplayBuffer.sample at 0x79eaca7dc2c0>", "_get_real_samples": "<function HerReplayBuffer._get_real_samples at 0x79eaca7dc360>", "_get_virtual_samples": "<function HerReplayBuffer._get_virtual_samples at 0x79eaca7dc400>", "_sample_goals": "<function HerReplayBuffer._sample_goals at 0x79eaca7dc4a0>", "truncate_last_trajectory": "<function HerReplayBuffer.truncate_last_trajectory at 0x79eaca7dc540>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x79eaca7d8100>"}, "replay_buffer_kwargs": {"n_sampled_goal": 4, "goal_selection_strategy": "future"}, "n_steps": 1, "train_freq": {":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>", ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"}, "use_sde_at_warmup": false, "target_entropy": -4.0, "ent_coef": "auto", "target_update_interval": 1, "lr_schedule": {":type:": "<class 'stable_baselines3.common.utils.FloatSchedule'>", ":serialized:": "gAWVeQAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMDUZsb2F0U2NoZWR1bGWUk5QpgZR9lIwOdmFsdWVfc2NoZWR1bGWUaACMEENvbnN0YW50U2NoZWR1bGWUk5QpgZR9lIwDdmFslEc/M6kqMFUyYXNic2Iu", "value_schedule": "ConstantSchedule(val=0.0003)"}, "batch_norm_stats": [], "batch_norm_stats_target": [], "system_info": {"OS": "Linux-6.1.123+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Mar 30 16:01:29 UTC 2025", "Python": "3.11.13", "Stable-Baselines3": "2.7.0", "PyTorch": "2.6.0+cu124", "GPU Enabled": "True", "Numpy": "2.0.2", "Cloudpickle": "3.1.1", "Gymnasium": "1.2.0", "OpenAI Gym": "0.25.2"}}

results.json

@@ -0,0 +1 @@
+{"mean_reward": -50.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-16T03:14:48.617879"}

sac-her-PandaPickAndPlace-v3-800k.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e5b62124a71776d8d4a3355e774a659e43ecea272e9bca6ea2e0eafed994439
+size 3302650

sac-her-PandaPickAndPlace-v3-800k/_stable_baselines3_version

@@ -0,0 +1 @@
+2.7.0

sac-her-PandaPickAndPlace-v3-800k/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65af6649b39c362094f6a3e84d7fc875b5dbae531d48d486b41bb40f62bfe916
+size 602958

sac-her-PandaPickAndPlace-v3-800k/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6531c1a11f9b98c62fa07e83c69fc4b3d7cbd11d0f12e59fa1efbba72e3aa4c9
+size 1189802

sac-her-PandaPickAndPlace-v3-800k/data

@@ -0,0 +1,120 @@
+{
+    "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 0x79eaca7df4c0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x79eaca7dacc0>"
+    },
+    "verbose": 0,
+    "policy_kwargs": {
+        "use_sde": false
+    },
+    "num_timesteps": 800000,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1755289801644837769,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdQAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWAQAAAAAAAAABlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksBhZSMAUOUdJRSlC4="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'collections.OrderedDict'>",
+        ":serialized:": "gAWVYAEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwTbnVtcHkuX2NvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYMAAAAAAAAAMmOvL1xdhU9k8GjPJSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsDhpSMAUOUdJRSlIwMZGVzaXJlZF9nb2FslGgHKJYMAAAAAAAAAGvzBLzY7eK9S0TTPZRoDksBSwOGlGgSdJRSlIwLb2JzZXJ2YXRpb26UaAcolkwAAAAAAAAA6wB0PXWM6b1u5Bo+0qHmvCyXmb2LS4A+4dKjPcmOvL1xdhU9k8GjPE/GnjcfGKs2IhMIOcMe4Lfdky84xneot3x89rrnX5y6kBQPOZRoDksBSxOGlGgSdJRSlHUu",
+        "achieved_goal": "[[-0.09206922  0.03648991  0.01998976]]",
+        "desired_goal": "[[-0.00811468 -0.11080521  0.1031576 ]]",
+        "observation": "[[ 5.9571188e-02 -1.1403743e-01  1.5126202e-01 -2.8153334e-02\n  -7.4995369e-02  2.5057635e-01  7.9992063e-02 -9.2069216e-02\n   3.6489908e-02  1.9989764e-02  1.8927412e-05  5.0990052e-06\n   1.2977098e-04 -2.6717205e-05  4.1860960e-05 -2.0082934e-05\n  -1.8805410e-03 -1.1930437e-03  1.3645203e-04]]"
+    },
+    "_episode_num": 19431,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": 0.20000099999999998,
+    "_stats_window_size": 100,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVhgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKImJiYmIiYmJiYmJiYmJiYmJiYmJiIiIiYiIiYmJiImIiImJiImIiYmJiYiJiYmJiIiIiYiIiYmJiImJiYmJiImIiImJiYmJiYmIiYiIiYiJiImJiIiIiYmJiImIiIiIiYmIiYllLg=="
+    },
+    "_n_updates": 799899,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.dict.Dict'>",
+        ":serialized:": "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",
+        "spaces": "{'achieved_goal': Box(-10.0, 10.0, (3,), float32), 'desired_goal': Box(-10.0, 10.0, (3,), float32), 'observation': Box(-10.0, 10.0, (19,), float32)}",
+        "_shape": null,
+        "dtype": null,
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            4
+        ],
+        "low": "[-1. -1. -1. -1.]",
+        "bounded_below": "[ True  True  True  True]",
+        "high": "[1. 1. 1. 1.]",
+        "bounded_above": "[ True  True  True  True]",
+        "low_repr": "-1.0",
+        "high_repr": "1.0",
+        "_np_random": "Generator(PCG64)"
+    },
+    "n_envs": 1,
+    "buffer_size": 1000000,
+    "batch_size": 256,
+    "learning_starts": 100,
+    "tau": 0.02,
+    "gamma": 0.95,
+    "gradient_steps": 1,
+    "optimize_memory_usage": false,
+    "replay_buffer_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVPwAAAAAAAACMJ3N0YWJsZV9iYXNlbGluZXMzLmhlci5oZXJfcmVwbGF5X2J1ZmZlcpSMD0hlclJlcGxheUJ1ZmZlcpSTlC4=",
+        "__module__": "stable_baselines3.her.her_replay_buffer",
+        "__annotations__": "{'env': typing.Optional[stable_baselines3.common.vec_env.base_vec_env.VecEnv]}",
+        "__doc__": "\n    Hindsight Experience Replay (HER) buffer.\n    Paper: https://arxiv.org/abs/1707.01495\n\n    Replay buffer for sampling HER (Hindsight Experience Replay) transitions.\n\n    .. note::\n\n      Compared to other implementations, the ``future`` goal sampling strategy is inclusive:\n      the current transition can be used when re-sampling.\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 env: The training environment\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    :param n_sampled_goal: Number of virtual transitions to create per real transition,\n        by sampling new goals.\n    :param goal_selection_strategy: Strategy for sampling goals for replay.\n        One of ['episode', 'final', 'future']\n    :param copy_info_dict: Whether to copy the info dictionary and pass it to\n        ``compute_reward()`` method.\n        Please note that the copy may cause a slowdown.\n        False by default.\n    ",
+        "__init__": "<function HerReplayBuffer.__init__ at 0x79eaca7bbe20>",
+        "__getstate__": "<function HerReplayBuffer.__getstate__ at 0x79eaca7bbec0>",
+        "__setstate__": "<function HerReplayBuffer.__setstate__ at 0x79eaca7bbf60>",
+        "set_env": "<function HerReplayBuffer.set_env at 0x79eaca7dc040>",
+        "add": "<function HerReplayBuffer.add at 0x79eaca7dc180>",
+        "_compute_episode_length": "<function HerReplayBuffer._compute_episode_length at 0x79eaca7dc220>",
+        "sample": "<function HerReplayBuffer.sample at 0x79eaca7dc2c0>",
+        "_get_real_samples": "<function HerReplayBuffer._get_real_samples at 0x79eaca7dc360>",
+        "_get_virtual_samples": "<function HerReplayBuffer._get_virtual_samples at 0x79eaca7dc400>",
+        "_sample_goals": "<function HerReplayBuffer._sample_goals at 0x79eaca7dc4a0>",
+        "truncate_last_trajectory": "<function HerReplayBuffer.truncate_last_trajectory at 0x79eaca7dc540>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x79eaca7d8100>"
+    },
+    "replay_buffer_kwargs": {
+        "n_sampled_goal": 4,
+        "goal_selection_strategy": "future"
+    },
+    "n_steps": 1,
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "target_entropy": -4.0,
+    "ent_coef": "auto",
+    "target_update_interval": 1,
+    "lr_schedule": {
+        ":type:": "<class 'stable_baselines3.common.utils.FloatSchedule'>",
+        ":serialized:": "gAWVeQAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMDUZsb2F0U2NoZWR1bGWUk5QpgZR9lIwOdmFsdWVfc2NoZWR1bGWUaACMEENvbnN0YW50U2NoZWR1bGWUk5QpgZR9lIwDdmFslEc/M6kqMFUyYXNic2Iu",
+        "value_schedule": "ConstantSchedule(val=0.0003)"
+    },
+    "batch_norm_stats": [],
+    "batch_norm_stats_target": []
+}

sac-her-PandaPickAndPlace-v3-800k/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9187a4349033a65728ee3d3cbf769c881114acb3c7612eb0e843902ec84cb04d
+size 1940

sac-her-PandaPickAndPlace-v3-800k/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01f022eb5418ff4260c663a7c326f7b801cc651da55f1fbd58d0a47d3328b04b
+size 1489782

sac-her-PandaPickAndPlace-v3-800k/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0709132d209de860e8080f5bc72e7814e8df00925ae3ef77febc0d77f41df10a
+size 1180

sac-her-PandaPickAndPlace-v3-800k/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-6.1.123+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Mar 30 16:01:29 UTC 2025
+- Python: 3.11.13
+- Stable-Baselines3: 2.7.0
+- PyTorch: 2.6.0+cu124
+- GPU Enabled: True
+- Numpy: 2.0.2
+- Cloudpickle: 3.1.1
+- Gymnasium: 1.2.0
+- OpenAI Gym: 0.25.2