Hugging Face's logo

crislmfroes
/
tqc-FetchPickAndPlace-v2

Reinforcement Learning
stable-baselines3
FetchPickAndPlace-v2
deep-reinforcement-learning
Eval Results
Model card Files
crislmfroes commited on
Commit
16163af
•
1 Parent(s): 35e4ff6

Initial commit

Browse files
Files changed (17) hide show
  1. .gitattributes +1 -0
  2. README.md +82 -0
  3. args.yml +83 -0
  4. config.yml +21 -0
  5. env_kwargs.yml +1 -0
  6. replay.mp4 +3 -0
  7. results.json +1 -0
  8. tqc-FetchPickAndPlace-v2.zip +3 -0
  9. tqc-FetchPickAndPlace-v2/_stable_baselines3_version +1 -0
  10. tqc-FetchPickAndPlace-v2/actor.optimizer.pth +3 -0
  11. tqc-FetchPickAndPlace-v2/critic.optimizer.pth +3 -0
  12. tqc-FetchPickAndPlace-v2/data +128 -0
  13. tqc-FetchPickAndPlace-v2/ent_coef_optimizer.pth +3 -0
  14. tqc-FetchPickAndPlace-v2/policy.pth +3 -0
  15. tqc-FetchPickAndPlace-v2/pytorch_variables.pth +3 -0
  16. tqc-FetchPickAndPlace-v2/system_info.txt +9 -0
  17. train_eval_metrics.zip +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ *.mp4 filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: stable-baselines3
3
+ tags:
4
+ - FetchPickAndPlace-v2
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: FetchPickAndPlace-v2
16
+ type: FetchPickAndPlace-v2
17
+ metrics:
18
+ - type: mean_reward
19
+ value: -12.70 +/- 12.81
20
+ name: mean_reward
21
+ verified: false
22
+ ---
23
+
24
+ # **TQC** Agent playing **FetchPickAndPlace-v2**
25
+ This is a trained model of a **TQC** agent playing **FetchPickAndPlace-v2**
26
+ using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
27
+ and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
28
+
29
+ The RL Zoo is a training framework for Stable Baselines3
30
+ reinforcement learning agents,
31
+ with hyperparameter optimization and pre-trained agents included.
32
+
33
+ ## Usage (with SB3 RL Zoo)
34
+
35
+ RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
36
+ SB3: https://github.com/DLR-RM/stable-baselines3<br/>
37
+ SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
38
+
39
+ Install the RL Zoo (with SB3 and SB3-Contrib):
40
+ ```bash
41
+ pip install rl_zoo3
42
+ ```
43
+
44
+ ```
45
+ # Download model and save it into the logs/ folder
46
+ python -m rl_zoo3.load_from_hub --algo tqc --env FetchPickAndPlace-v2 -orga crislmfroes -f logs/
47
+ python -m rl_zoo3.enjoy --algo tqc --env FetchPickAndPlace-v2 -f logs/
48
+ ```
49
+
50
+ If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
51
+ ```
52
+ python -m rl_zoo3.load_from_hub --algo tqc --env FetchPickAndPlace-v2 -orga crislmfroes -f logs/
53
+ python -m rl_zoo3.enjoy --algo tqc --env FetchPickAndPlace-v2 -f logs/
54
+ ```
55
+
56
+ ## Training (with the RL Zoo)
57
+ ```
58
+ python -m rl_zoo3.train --algo tqc --env FetchPickAndPlace-v2 -f logs/
59
+ # Upload the model and generate video (when possible)
60
+ python -m rl_zoo3.push_to_hub --algo tqc --env FetchPickAndPlace-v2 -f logs/ -orga crislmfroes
61
+ ```
62
+
63
+ ## Hyperparameters
64
+ ```python
65
+ OrderedDict([('batch_size', 2048),
66
+ ('buffer_size', 1000000),
67
+ ('gamma', 0.95),
68
+ ('learning_rate', 0.001),
69
+ ('n_timesteps', 1000000.0),
70
+ ('policy', 'MultiInputPolicy'),
71
+ ('policy_kwargs', 'dict(net_arch=[512, 512, 512], n_critics=2)'),
72
+ ('replay_buffer_class', 'HerReplayBuffer'),
73
+ ('replay_buffer_kwargs',
74
+ "dict( goal_selection_strategy='future', n_sampled_goal=4, )"),
75
+ ('tau', 0.05),
76
+ ('normalize', False)])
77
+ ```
78
+
79
+ # Environment Arguments
80
+ ```python
81
+ {'render_mode': 'rgb_array'}
82
+ ```
args.yml ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - algo
3
+ - tqc
4
+ - - conf_file
5
+ - null
6
+ - - device
7
+ - auto
8
+ - - env
9
+ - FetchPickAndPlace-v2
10
+ - - env_kwargs
11
+ - null
12
+ - - eval_env_kwargs
13
+ - null
14
+ - - eval_episodes
15
+ - 5
16
+ - - eval_freq
17
+ - 25000
18
+ - - gym_packages
19
+ - []
20
+ - - hyperparams
21
+ - null
22
+ - - log_folder
23
+ - logs
24
+ - - log_interval
25
+ - -1
26
+ - - max_total_trials
27
+ - null
28
+ - - n_eval_envs
29
+ - 1
30
+ - - n_evaluations
31
+ - null
32
+ - - n_jobs
33
+ - 1
34
+ - - n_startup_trials
35
+ - 10
36
+ - - n_timesteps
37
+ - -1
38
+ - - n_trials
39
+ - 500
40
+ - - no_optim_plots
41
+ - false
42
+ - - num_threads
43
+ - -1
44
+ - - optimization_log_path
45
+ - null
46
+ - - optimize_hyperparameters
47
+ - false
48
+ - - progress
49
+ - false
50
+ - - pruner
51
+ - median
52
+ - - sampler
53
+ - tpe
54
+ - - save_freq
55
+ - -1
56
+ - - save_replay_buffer
57
+ - false
58
+ - - seed
59
+ - 2759187045
60
+ - - storage
61
+ - null
62
+ - - study_name
63
+ - null
64
+ - - tensorboard_log
65
+ - ''
66
+ - - track
67
+ - false
68
+ - - trained_agent
69
+ - ''
70
+ - - truncate_last_trajectory
71
+ - true
72
+ - - uuid
73
+ - false
74
+ - - vec_env
75
+ - dummy
76
+ - - verbose
77
+ - 1
78
+ - - wandb_entity
79
+ - null
80
+ - - wandb_project_name
81
+ - sb3
82
+ - - wandb_tags
83
+ - []
config.yml ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - batch_size
3
+ - 2048
4
+ - - buffer_size
5
+ - 1000000
6
+ - - gamma
7
+ - 0.95
8
+ - - learning_rate
9
+ - 0.001
10
+ - - n_timesteps
11
+ - 1000000.0
12
+ - - policy
13
+ - MultiInputPolicy
14
+ - - policy_kwargs
15
+ - dict(net_arch=[512, 512, 512], n_critics=2)
16
+ - - replay_buffer_class
17
+ - HerReplayBuffer
18
+ - - replay_buffer_kwargs
19
+ - dict( goal_selection_strategy='future', n_sampled_goal=4, )
20
+ - - tau
21
+ - 0.05
env_kwargs.yml ADDED
@@ -0,0 +1 @@
 
 
1
+ render_mode: rgb_array
replay.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed367db2ab47186658b4c4836c1e2a4fdd1a585c929489057945b2fe5f529bff
3
+ size 595843
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": -12.7, "std_reward": 12.814444974324873, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-19T11:17:33.928883"}
tqc-FetchPickAndPlace-v2.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce75f14b54ca5b6d2fa8d88f8221267149961937658c934a54edb3cd63370d8a
3
+ size 24421581
tqc-FetchPickAndPlace-v2/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 2.3.0a1
tqc-FetchPickAndPlace-v2/actor.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3af7673c45d858fe486929056bc1c1fedf52e3987d03d534c38b91c1b9944a36
3
+ size 4374908
tqc-FetchPickAndPlace-v2/critic.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cbe5b3f1dcac60ea7c6ec1cebaa241314beed6f87f0e471ab4862e0f94a36c4
3
+ size 8918534
tqc-FetchPickAndPlace-v2/data ADDED
@@ -0,0 +1,128 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 0x7fc95924b520>",
8
+ "__abstractmethods__": "frozenset()",
9
+ "_abc_impl": "<_abc._abc_data object at 0x7fc9592428c0>"
10
+ },
11
+ "verbose": 1,
12
+ "policy_kwargs": {
13
+ "net_arch": [
14
+ 512,
15
+ 512,
16
+ 512
17
+ ],
18
+ "n_critics": 2,
19
+ "use_sde": false
20
+ },
21
+ "num_timesteps": 1000000,
22
+ "_total_timesteps": 1000000,
23
+ "_num_timesteps_at_start": 0,
24
+ "seed": 0,
25
+ "action_noise": null,
26
+ "start_time": 1705622865696400921,
27
+ "learning_rate": {
28
+ ":type:": "<class 'function'>",
29
+ ":serialized:": "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"
30
+ },
31
+ "tensorboard_log": null,
32
+ "_last_obs": null,
33
+ "_last_episode_starts": {
34
+ ":type:": "<class 'numpy.ndarray'>",
35
+ ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
36
+ },
37
+ "_last_original_obs": {
38
+ ":type:": "<class 'collections.OrderedDict'>",
39
+ ":serialized:": "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",
40
+ "achieved_goal": "[[1.42461079 0.83340399 0.42478449]]",
41
+ "desired_goal": "[[1.41283586 0.83675756 0.42469975]]",
42
+ "observation": "[[ 1.13040328e+00 9.59626720e-01 4.17771082e-01 1.42461079e+00\n 8.33403990e-01 4.24784489e-01 2.94207504e-01 -1.26222730e-01\n 7.01340720e-03 4.30266584e-02 5.04638626e-02 1.02568372e-11\n -1.13155811e-11 9.69893439e-02 1.82668417e-03 -6.39392343e-03\n 1.58372526e-04 -5.58940654e-12 6.16635967e-12 -5.42567563e-18\n -1.82668417e-03 6.39392343e-03 -1.58372525e-04 -7.08411825e-03\n 4.13275752e-03]]"
43
+ },
44
+ "_episode_num": 20000,
45
+ "use_sde": false,
46
+ "sde_sample_freq": -1,
47
+ "_current_progress_remaining": 0.0,
48
+ "_stats_window_size": 100,
49
+ "ep_info_buffer": {
50
+ ":type:": "<class 'collections.deque'>",
51
+ ":serialized:": "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"
52
+ },
53
+ "ep_success_buffer": {
54
+ ":type:": "<class 'collections.deque'>",
55
+ ":serialized:": "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"
56
+ },
57
+ "_n_updates": 999900,
58
+ "observation_space": {
59
+ ":type:": "<class 'gymnasium.spaces.dict.Dict'>",
60
+ ":serialized:": "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",
61
+ "spaces": "OrderedDict([('achieved_goal', Box(-inf, inf, (3,), float64)), ('desired_goal', Box(-inf, inf, (3,), float64)), ('observation', Box(-inf, inf, (25,), float64))])",
62
+ "_shape": null,
63
+ "dtype": null,
64
+ "_np_random": null
65
+ },
66
+ "action_space": {
67
+ ":type:": "<class 'gymnasium.spaces.box.Box'>",
68
+ ":serialized:": "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",
69
+ "dtype": "float32",
70
+ "bounded_below": "[ True True True True]",
71
+ "bounded_above": "[ True True True True]",
72
+ "_shape": [
73
+ 4
74
+ ],
75
+ "low": "[-1. -1. -1. -1.]",
76
+ "high": "[1. 1. 1. 1.]",
77
+ "low_repr": "-1.0",
78
+ "high_repr": "1.0",
79
+ "_np_random": "Generator(PCG64)"
80
+ },
81
+ "n_envs": 1,
82
+ "buffer_size": 1,
83
+ "batch_size": 2048,
84
+ "learning_starts": 100,
85
+ "tau": 0.05,
86
+ "gamma": 0.95,
87
+ "gradient_steps": 1,
88
+ "optimize_memory_usage": false,
89
+ "replay_buffer_class": {
90
+ ":type:": "<class 'abc.ABCMeta'>",
91
+ ":serialized:": "gAWVPwAAAAAAAACMJ3N0YWJsZV9iYXNlbGluZXMzLmhlci5oZXJfcmVwbGF5X2J1ZmZlcpSMD0hlclJlcGxheUJ1ZmZlcpSTlC4=",
92
+ "__module__": "stable_baselines3.her.her_replay_buffer",
93
+ "__annotations__": "{'env': typing.Optional[stable_baselines3.common.vec_env.base_vec_env.VecEnv]}",
94
+ "__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 ",
95
+ "__init__": "<function HerReplayBuffer.__init__ at 0x7fc959ddd990>",
96
+ "__getstate__": "<function HerReplayBuffer.__getstate__ at 0x7fc959ddda20>",
97
+ "__setstate__": "<function HerReplayBuffer.__setstate__ at 0x7fc959dddab0>",
98
+ "set_env": "<function HerReplayBuffer.set_env at 0x7fc959dddb40>",
99
+ "add": "<function HerReplayBuffer.add at 0x7fc959dddbd0>",
100
+ "_compute_episode_length": "<function HerReplayBuffer._compute_episode_length at 0x7fc959dddc60>",
101
+ "sample": "<function HerReplayBuffer.sample at 0x7fc959dddcf0>",
102
+ "_get_real_samples": "<function HerReplayBuffer._get_real_samples at 0x7fc959dddd80>",
103
+ "_get_virtual_samples": "<function HerReplayBuffer._get_virtual_samples at 0x7fc959ddde10>",
104
+ "_sample_goals": "<function HerReplayBuffer._sample_goals at 0x7fc959dddea0>",
105
+ "truncate_last_trajectory": "<function HerReplayBuffer.truncate_last_trajectory at 0x7fc959dddf30>",
106
+ "__abstractmethods__": "frozenset()",
107
+ "_abc_impl": "<_abc._abc_data object at 0x7fc959de33c0>"
108
+ },
109
+ "replay_buffer_kwargs": {
110
+ "goal_selection_strategy": "future",
111
+ "n_sampled_goal": 4
112
+ },
113
+ "train_freq": {
114
+ ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
115
+ ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
116
+ },
117
+ "use_sde_at_warmup": false,
118
+ "target_entropy": -4.0,
119
+ "ent_coef": "auto",
120
+ "target_update_interval": 1,
121
+ "top_quantiles_to_drop_per_net": 2,
122
+ "lr_schedule": {
123
+ ":type:": "<class 'function'>",
124
+ ":serialized:": "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"
125
+ },
126
+ "batch_norm_stats": [],
127
+ "batch_norm_stats_target": []
128
+ }
tqc-FetchPickAndPlace-v2/ent_coef_optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fa6746166bf8ab65293cec352d58f806d4dff125a080b20547fa275cc38c7ea
3
+ size 1940
tqc-FetchPickAndPlace-v2/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db2e6c43bbb3d5612175c7ae9497fbf4b778c75169fc675fc43b39cb59a99384
3
+ size 11103640
tqc-FetchPickAndPlace-v2/pytorch_variables.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e60926d9dca528b00a889cfc83ca796b87bd803f0ac5402130f4056f3e031a27
3
+ size 1180
tqc-FetchPickAndPlace-v2/system_info.txt ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ - OS: Linux-5.15.0-91-generic-x86_64-with-glibc2.31 # 101~20.04.1-Ubuntu SMP Thu Nov 16 14:22:28 UTC 2023
2
+ - Python: 3.10.13
3
+ - Stable-Baselines3: 2.3.0a1
4
+ - PyTorch: 2.1.2+cu121
5
+ - GPU Enabled: True
6
+ - Numpy: 1.24.3
7
+ - Cloudpickle: 3.0.0
8
+ - Gymnasium: 0.29.1
9
+ - OpenAI Gym: 0.26.2
train_eval_metrics.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f79181806896b6d4e083eeab00f308bda0e036f9aeeb068d2c1d658200cc120
3
+ size 445528