gracetxgao commited on
Commit
24d7c7a
1 Parent(s): d489d0b

Initial commit

Browse files
README.md ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: stable-baselines3
3
+ tags:
4
+ - PandaReachDense-v3
5
+ - deep-reinforcement-learning
6
+ - reinforcement-learning
7
+ - stable-baselines3
8
+ model-index:
9
+ - name: TQC
10
+ results:
11
+ - task:
12
+ type: reinforcement-learning
13
+ name: reinforcement-learning
14
+ dataset:
15
+ name: PandaReachDense-v3
16
+ type: PandaReachDense-v3
17
+ metrics:
18
+ - type: mean_reward
19
+ value: -0.14 +/- 0.09
20
+ name: mean_reward
21
+ verified: false
22
+ ---
23
+
24
+ # **TQC** Agent playing **PandaReachDense-v3**
25
+ This is a trained model of a **TQC** agent playing **PandaReachDense-v3**
26
+ using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
27
+
28
+ ## Usage (with Stable-baselines3)
29
+ TODO: Add your code
30
+
31
+
32
+ ```python
33
+ from stable_baselines3 import ...
34
+ from huggingface_sb3 import load_from_hub
35
+
36
+ ...
37
+ ```
config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVMQAAAAAAAACMGHNiM19jb250cmliLnRxYy5wb2xpY2llc5SMEE11bHRpSW5wdXRQb2xpY3mUk5Qu", "__module__": "sb3_contrib.tqc.policies", "__doc__": "\n Policy class (with both actor and critic) for TQC.\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_quantiles: Number of quantiles for the critic.\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 0x7e4002e860e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7e4002e550c0>"}, "verbose": 1, "policy_kwargs": {"use_sde": false}, "num_timesteps": 1000000, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1717182166260596827, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[-0.03831719 -0.55145735 0.02041981]\n [-1.0772197 -1.6307772 0.422943 ]\n [ 0.36119643 -0.04175475 0.560607 ]\n [ 0.36119643 -0.04175475 0.560607 ]]", "desired_goal": "[[-0.84708834 -0.57216364 -0.24094032]\n [-1.4838163 -1.1612904 0.48850772]\n [-0.6397504 0.03909931 0.91639274]\n [ 1.0423585 -0.22814794 -0.4502616 ]]", "observation": "[[-0.03831719 -0.55145735 0.02041981 -2.2500594 -1.769259 -1.5508934 ]\n [-1.0772197 -1.6307772 0.422943 -0.93074274 -1.3001424 -0.32195956]\n [ 0.36119643 -0.04175475 0.560607 0.51321447 -0.00630055 0.36625364]\n [ 0.36119643 -0.04175475 0.560607 0.51321447 -0.00630055 0.36625364]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAEBAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 1.8825505e-02 -2.4782622e-02 1.6665936e-01]\n [-3.2179523e-02 -7.7261023e-02 1.8956600e-01]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]]", "desired_goal": "[[-0.08388247 -0.05125091 0.12087391]\n [-0.14181706 -0.10421489 0.18700217]\n [-0.06501722 0.00370317 0.22579217]\n [ 0.0880345 -0.02032303 0.10189784]]", "observation": "[[ 1.8825505e-02 -2.4782622e-02 1.6665936e-01 -1.0122261e+00\n -1.0439783e+00 -1.2029680e+00]\n [-3.2179523e-02 -7.7261023e-02 1.8956600e-01 -5.2894187e-01\n -7.6617968e-01 -4.3183878e-01]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]]"}, "_episode_num": 302565, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.0, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVhgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIhlLg=="}, "_n_updates": 249975, "buffer_size": 1000000, "batch_size": 256, "learning_starts": 100, "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", "__annotations__": "{'observation_space': <class 'gymnasium.spaces.dict.Dict'>, 'obs_shape': typing.Dict[str, typing.Tuple[int, ...]], 'observations': typing.Dict[str, numpy.ndarray], 'next_observations': typing.Dict[str, numpy.ndarray]}", "__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 0x7e40151a4d30>", "add": "<function DictReplayBuffer.add at 0x7e40151a4dc0>", "sample": "<function DictReplayBuffer.sample at 0x7e40151a4e50>", "_get_samples": "<function DictReplayBuffer._get_samples at 0x7e40151a4ee0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7e4015485d80>"}, "replay_buffer_kwargs": {}, "train_freq": {":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>", ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"}, "use_sde_at_warmup": false, "target_entropy": -3.0, "ent_coef": "auto", "target_update_interval": 1, "top_quantiles_to_drop_per_net": 2, "observation_space": {":type:": "<class 'gymnasium.spaces.dict.Dict'>", ":serialized:": "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", "spaces": "OrderedDict([('achieved_goal', Box(-10.0, 10.0, (3,), float32)), ('desired_goal', Box(-10.0, 10.0, (3,), float32)), ('observation', Box(-10.0, 10.0, (6,), float32))])", "_shape": null, "dtype": null, "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True]", "bounded_above": "[ True True True]", "_shape": [3], "low": "[-1. -1. -1.]", "high": "[1. 1. 1.]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": "Generator(PCG64)"}, "n_envs": 4, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "batch_norm_stats": [], "batch_norm_stats_target": [], "system_info": {"OS": "Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Apr 28 14:29:16 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.3.2", "PyTorch": "2.3.0+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.1", "OpenAI Gym": "0.25.2"}}
replay.mp4 ADDED
Binary file (654 kB). View file
 
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": -0.1433590820990503, "std_reward": 0.08940681705155903, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-31T20:48:41.046865"}
tqc-PandaReachDense-v3.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cac7cd21bb37f9cbdc075ab07efefad2b85c51fd23b3d2c52416d46cdd3dfb79
3
+ size 3340171
tqc-PandaReachDense-v3/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 2.3.2
tqc-PandaReachDense-v3/actor.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63ee6eca162fbc1e86acfa16e8c353e8e90e684ce37263592d0315d5e0333bd2
3
+ size 572238
tqc-PandaReachDense-v3/critic.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0da431eab9e57ff6fc65c1df15da7ab5f138b87e4ef10177ecd484c78763d3f
3
+ size 1231018
tqc-PandaReachDense-v3/data ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "policy_class": {
3
+ ":type:": "<class 'abc.ABCMeta'>",
4
+ ":serialized:": "gAWVMQAAAAAAAACMGHNiM19jb250cmliLnRxYy5wb2xpY2llc5SMEE11bHRpSW5wdXRQb2xpY3mUk5Qu",
5
+ "__module__": "sb3_contrib.tqc.policies",
6
+ "__doc__": "\n Policy class (with both actor and critic) for TQC.\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_quantiles: Number of quantiles for the critic.\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 ",
7
+ "__init__": "<function MultiInputPolicy.__init__ at 0x7e4002e860e0>",
8
+ "__abstractmethods__": "frozenset()",
9
+ "_abc_impl": "<_abc._abc_data object at 0x7e4002e550c0>"
10
+ },
11
+ "verbose": 1,
12
+ "policy_kwargs": {
13
+ "use_sde": false
14
+ },
15
+ "num_timesteps": 1000000,
16
+ "_total_timesteps": 1000000,
17
+ "_num_timesteps_at_start": 0,
18
+ "seed": null,
19
+ "action_noise": null,
20
+ "start_time": 1717182166260596827,
21
+ "learning_rate": 0.0003,
22
+ "tensorboard_log": null,
23
+ "_last_obs": {
24
+ ":type:": "<class 'collections.OrderedDict'>",
25
+ ":serialized:": "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",
26
+ "achieved_goal": "[[-0.03831719 -0.55145735 0.02041981]\n [-1.0772197 -1.6307772 0.422943 ]\n [ 0.36119643 -0.04175475 0.560607 ]\n [ 0.36119643 -0.04175475 0.560607 ]]",
27
+ "desired_goal": "[[-0.84708834 -0.57216364 -0.24094032]\n [-1.4838163 -1.1612904 0.48850772]\n [-0.6397504 0.03909931 0.91639274]\n [ 1.0423585 -0.22814794 -0.4502616 ]]",
28
+ "observation": "[[-0.03831719 -0.55145735 0.02041981 -2.2500594 -1.769259 -1.5508934 ]\n [-1.0772197 -1.6307772 0.422943 -0.93074274 -1.3001424 -0.32195956]\n [ 0.36119643 -0.04175475 0.560607 0.51321447 -0.00630055 0.36625364]\n [ 0.36119643 -0.04175475 0.560607 0.51321447 -0.00630055 0.36625364]]"
29
+ },
30
+ "_last_episode_starts": {
31
+ ":type:": "<class 'numpy.ndarray'>",
32
+ ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAEBAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="
33
+ },
34
+ "_last_original_obs": {
35
+ ":type:": "<class 'collections.OrderedDict'>",
36
+ ":serialized:": "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",
37
+ "achieved_goal": "[[ 1.8825505e-02 -2.4782622e-02 1.6665936e-01]\n [-3.2179523e-02 -7.7261023e-02 1.8956600e-01]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]]",
38
+ "desired_goal": "[[-0.08388247 -0.05125091 0.12087391]\n [-0.14181706 -0.10421489 0.18700217]\n [-0.06501722 0.00370317 0.22579217]\n [ 0.0880345 -0.02032303 0.10189784]]",
39
+ "observation": "[[ 1.8825505e-02 -2.4782622e-02 1.6665936e-01 -1.0122261e+00\n -1.0439783e+00 -1.2029680e+00]\n [-3.2179523e-02 -7.7261023e-02 1.8956600e-01 -5.2894187e-01\n -7.6617968e-01 -4.3183878e-01]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]]"
40
+ },
41
+ "_episode_num": 302565,
42
+ "use_sde": false,
43
+ "sde_sample_freq": -1,
44
+ "_current_progress_remaining": 0.0,
45
+ "_stats_window_size": 100,
46
+ "ep_info_buffer": {
47
+ ":type:": "<class 'collections.deque'>",
48
+ ":serialized:": "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"
49
+ },
50
+ "ep_success_buffer": {
51
+ ":type:": "<class 'collections.deque'>",
52
+ ":serialized:": "gAWVhgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIhlLg=="
53
+ },
54
+ "_n_updates": 249975,
55
+ "buffer_size": 1000000,
56
+ "batch_size": 256,
57
+ "learning_starts": 100,
58
+ "tau": 0.005,
59
+ "gamma": 0.99,
60
+ "gradient_steps": 1,
61
+ "optimize_memory_usage": false,
62
+ "replay_buffer_class": {
63
+ ":type:": "<class 'abc.ABCMeta'>",
64
+ ":serialized:": "gAWVOQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwQRGljdFJlcGxheUJ1ZmZlcpSTlC4=",
65
+ "__module__": "stable_baselines3.common.buffers",
66
+ "__annotations__": "{'observation_space': <class 'gymnasium.spaces.dict.Dict'>, 'obs_shape': typing.Dict[str, typing.Tuple[int, ...]], 'observations': typing.Dict[str, numpy.ndarray], 'next_observations': typing.Dict[str, numpy.ndarray]}",
67
+ "__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 ",
68
+ "__init__": "<function DictReplayBuffer.__init__ at 0x7e40151a4d30>",
69
+ "add": "<function DictReplayBuffer.add at 0x7e40151a4dc0>",
70
+ "sample": "<function DictReplayBuffer.sample at 0x7e40151a4e50>",
71
+ "_get_samples": "<function DictReplayBuffer._get_samples at 0x7e40151a4ee0>",
72
+ "__abstractmethods__": "frozenset()",
73
+ "_abc_impl": "<_abc._abc_data object at 0x7e4015485d80>"
74
+ },
75
+ "replay_buffer_kwargs": {},
76
+ "train_freq": {
77
+ ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
78
+ ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
79
+ },
80
+ "use_sde_at_warmup": false,
81
+ "target_entropy": -3.0,
82
+ "ent_coef": "auto",
83
+ "target_update_interval": 1,
84
+ "top_quantiles_to_drop_per_net": 2,
85
+ "observation_space": {
86
+ ":type:": "<class 'gymnasium.spaces.dict.Dict'>",
87
+ ":serialized:": "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",
88
+ "spaces": "OrderedDict([('achieved_goal', Box(-10.0, 10.0, (3,), float32)), ('desired_goal', Box(-10.0, 10.0, (3,), float32)), ('observation', Box(-10.0, 10.0, (6,), float32))])",
89
+ "_shape": null,
90
+ "dtype": null,
91
+ "_np_random": null
92
+ },
93
+ "action_space": {
94
+ ":type:": "<class 'gymnasium.spaces.box.Box'>",
95
+ ":serialized:": "gAWVYQIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWAwAAAAAAAAABAQGUaAiMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLA4WUjAFDlHSUUpSMDWJvdW5kZWRfYWJvdmWUaBEolgMAAAAAAAAAAQEBlGgVSwOFlGgZdJRSlIwGX3NoYXBllEsDhZSMA2xvd5RoESiWDAAAAAAAAAAAAIC/AACAvwAAgL+UaAtLA4WUaBl0lFKUjARoaWdolGgRKJYMAAAAAAAAAAAAgD8AAIA/AACAP5RoC0sDhZRoGXSUUpSMCGxvd19yZXBylIwELTEuMJSMCWhpZ2hfcmVwcpSMAzEuMJSMCl9ucF9yYW5kb22UjBRudW1weS5yYW5kb20uX3BpY2tsZZSMEF9fZ2VuZXJhdG9yX2N0b3KUk5SMBVBDRzY0lGgyjBRfX2JpdF9nZW5lcmF0b3JfY3RvcpSTlIaUUpR9lCiMDWJpdF9nZW5lcmF0b3KUjAVQQ0c2NJSMBXN0YXRllH2UKGg9ihDJA/ZHxbwgKoA0skY+rxY3jANpbmOUihFRqvJRimQN1OaIqm4xs5qpAHWMCmhhc191aW50MzKUSwCMCHVpbnRlZ2VylEsAdWJ1Yi4=",
96
+ "dtype": "float32",
97
+ "bounded_below": "[ True True True]",
98
+ "bounded_above": "[ True True True]",
99
+ "_shape": [
100
+ 3
101
+ ],
102
+ "low": "[-1. -1. -1.]",
103
+ "high": "[1. 1. 1.]",
104
+ "low_repr": "-1.0",
105
+ "high_repr": "1.0",
106
+ "_np_random": "Generator(PCG64)"
107
+ },
108
+ "n_envs": 4,
109
+ "lr_schedule": {
110
+ ":type:": "<class 'function'>",
111
+ ":serialized:": "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"
112
+ },
113
+ "batch_norm_stats": [],
114
+ "batch_norm_stats_target": []
115
+ }
tqc-PandaReachDense-v3/ent_coef_optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50a509eea3a3ab6f7b011eca68cf203d328c27982772ca558d7c3bf0eac54344
3
+ size 1940
tqc-PandaReachDense-v3/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f6fa5eb2b6ff5fa19d91120d0ae8d092a5ebd01230b53bca4a009c6e9c26233
3
+ size 1515638
tqc-PandaReachDense-v3/pytorch_variables.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fb45f821bf2bacd5a71abfa11ee5d19dd84730b284c097c4be08b4ae82682c5
3
+ size 1180
tqc-PandaReachDense-v3/system_info.txt ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ - OS: Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Apr 28 14:29:16 UTC 2024
2
+ - Python: 3.10.12
3
+ - Stable-Baselines3: 2.3.2
4
+ - PyTorch: 2.3.0+cu121
5
+ - GPU Enabled: True
6
+ - Numpy: 1.25.2
7
+ - Cloudpickle: 2.2.1
8
+ - Gymnasium: 0.29.1
9
+ - OpenAI Gym: 0.25.2
vec_normalize.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:868904c77cb407131e88f83a8120238926e496cb187eeffa18efb0014731ea45
3
+ size 2848