Quentin Gallouédec commited on
Commit
9403e57
1 Parent(s): b652501

Initial commit

Browse files
.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ *.mp4 filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: stable-baselines3
3
+ tags:
4
+ - CartpoleSwingupSparseDMC-v0
5
+ - deep-reinforcement-learning
6
+ - reinforcement-learning
7
+ - stable-baselines3
8
+ model-index:
9
+ - name: DDPG
10
+ results:
11
+ - task:
12
+ type: reinforcement-learning
13
+ name: reinforcement-learning
14
+ dataset:
15
+ name: CartpoleSwingupSparseDMC-v0
16
+ type: CartpoleSwingupSparseDMC-v0
17
+ metrics:
18
+ - type: mean_reward
19
+ value: 344.20 +/- 1.66
20
+ name: mean_reward
21
+ verified: false
22
+ ---
23
+
24
+ # **DDPG** Agent playing **CartpoleSwingupSparseDMC-v0**
25
+ This is a trained model of a **DDPG** agent playing **CartpoleSwingupSparseDMC-v0**
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 ddpg --env CartpoleSwingupSparseDMC-v0 -orga qgallouedec -f logs/
47
+ python -m rl_zoo3.enjoy --algo ddpg --env CartpoleSwingupSparseDMC-v0 -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 ddpg --env CartpoleSwingupSparseDMC-v0 -orga qgallouedec -f logs/
53
+ python -m rl_zoo3.enjoy --algo ddpg --env CartpoleSwingupSparseDMC-v0 -f logs/
54
+ ```
55
+
56
+ ## Training (with the RL Zoo)
57
+ ```
58
+ python -m rl_zoo3.train --algo ddpg --env CartpoleSwingupSparseDMC-v0 -f logs/
59
+ # Upload the model and generate video (when possible)
60
+ python -m rl_zoo3.push_to_hub --algo ddpg --env CartpoleSwingupSparseDMC-v0 -f logs/ -orga qgallouedec
61
+ ```
62
+
63
+ ## Hyperparameters
64
+ ```python
65
+ OrderedDict([('batch_size', 64),
66
+ ('gamma', 0.99),
67
+ ('learning_rate', 0.0001),
68
+ ('n_timesteps', 1000000.0),
69
+ ('noise_std', 0.3),
70
+ ('noise_type', 'ornstein-uhlenbeck'),
71
+ ('policy', 'MlpPolicy'),
72
+ ('policy_kwargs',
73
+ 'dict(net_arch=dict(pi=[300, 200], qf=[400, 300]))'),
74
+ ('normalize', False)])
75
+ ```
args.yml ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - algo
3
+ - ddpg
4
+ - - conf_file
5
+ - null
6
+ - - device
7
+ - auto
8
+ - - env
9
+ - CartpoleSwingupSparseDMC-v0
10
+ - - env_kwargs
11
+ - null
12
+ - - eval_episodes
13
+ - 20
14
+ - - eval_freq
15
+ - 25000
16
+ - - gym_packages
17
+ - []
18
+ - - hyperparams
19
+ - null
20
+ - - log_folder
21
+ - logs
22
+ - - log_interval
23
+ - -1
24
+ - - max_total_trials
25
+ - null
26
+ - - n_eval_envs
27
+ - 5
28
+ - - n_evaluations
29
+ - null
30
+ - - n_jobs
31
+ - 1
32
+ - - n_startup_trials
33
+ - 10
34
+ - - n_timesteps
35
+ - -1
36
+ - - n_trials
37
+ - 500
38
+ - - no_optim_plots
39
+ - false
40
+ - - num_threads
41
+ - -1
42
+ - - optimization_log_path
43
+ - null
44
+ - - optimize_hyperparameters
45
+ - false
46
+ - - progress
47
+ - false
48
+ - - pruner
49
+ - median
50
+ - - sampler
51
+ - tpe
52
+ - - save_freq
53
+ - -1
54
+ - - save_replay_buffer
55
+ - false
56
+ - - seed
57
+ - 1058068409
58
+ - - storage
59
+ - null
60
+ - - study_name
61
+ - null
62
+ - - tensorboard_log
63
+ - runs/CartpoleSwingupSparseDMC-v0__ddpg__1058068409__1673811016
64
+ - - track
65
+ - true
66
+ - - trained_agent
67
+ - ''
68
+ - - truncate_last_trajectory
69
+ - true
70
+ - - uuid
71
+ - false
72
+ - - vec_env
73
+ - dummy
74
+ - - verbose
75
+ - 1
76
+ - - wandb_entity
77
+ - qgallouedec
78
+ - - wandb_project_name
79
+ - dmc
80
+ - - wandb_tags
81
+ - []
82
+ - - yaml_file
83
+ - null
config.yml ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - batch_size
3
+ - 64
4
+ - - gamma
5
+ - 0.99
6
+ - - learning_rate
7
+ - 0.0001
8
+ - - n_timesteps
9
+ - 1000000.0
10
+ - - noise_std
11
+ - 0.3
12
+ - - noise_type
13
+ - ornstein-uhlenbeck
14
+ - - policy
15
+ - MlpPolicy
16
+ - - policy_kwargs
17
+ - dict(net_arch=dict(pi=[300, 200], qf=[400, 300]))
ddpg-CartpoleSwingupSparseDMC-v0.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ea9a66258917cc3c66941e4f9014be21ae1a3f67bb4cfdca384cc89cabafd2e
3
+ size 3012006
ddpg-CartpoleSwingupSparseDMC-v0/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 1.7.0
ddpg-CartpoleSwingupSparseDMC-v0/actor.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9201f7c7f7b5763e506c6d6c6d40426249d5bc74bbbea8a935ac00455bdf3df7
3
+ size 502319
ddpg-CartpoleSwingupSparseDMC-v0/critic.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19c873f7d4ccd134af1ca9b059b04f6eef641fb744512c4d3df0823aede6f0c5
3
+ size 991855
ddpg-CartpoleSwingupSparseDMC-v0/data ADDED
@@ -0,0 +1,137 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "policy_class": {
3
+ ":type:": "<class 'abc.ABCMeta'>",
4
+ ":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnRkMy5wb2xpY2llc5SMCVREM1BvbGljeZSTlC4=",
5
+ "__module__": "stable_baselines3.td3.policies",
6
+ "__doc__": "\n Policy class (with both actor and critic) for TD3.\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 features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\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 ",
7
+ "__init__": "<function TD3Policy.__init__ at 0x12af98280>",
8
+ "_build": "<function TD3Policy._build at 0x12af98310>",
9
+ "_get_constructor_parameters": "<function TD3Policy._get_constructor_parameters at 0x12af983a0>",
10
+ "make_actor": "<function TD3Policy.make_actor at 0x12af98430>",
11
+ "make_critic": "<function TD3Policy.make_critic at 0x12af984c0>",
12
+ "forward": "<function TD3Policy.forward at 0x12af98550>",
13
+ "_predict": "<function TD3Policy._predict at 0x12af985e0>",
14
+ "set_training_mode": "<function TD3Policy.set_training_mode at 0x12af98670>",
15
+ "__abstractmethods__": "frozenset()",
16
+ "_abc_impl": "<_abc._abc_data object at 0x12af92dc0>"
17
+ },
18
+ "verbose": 1,
19
+ "policy_kwargs": {
20
+ "net_arch": {
21
+ "pi": [
22
+ 300,
23
+ 200
24
+ ],
25
+ "qf": [
26
+ 400,
27
+ 300
28
+ ]
29
+ },
30
+ "n_critics": 1
31
+ },
32
+ "observation_space": {
33
+ ":type:": "<class 'gym.spaces.box.Box'>",
34
+ ":serialized:": "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",
35
+ "dtype": "float32",
36
+ "_shape": [
37
+ 5
38
+ ],
39
+ "low": "[-inf -inf -inf -inf -inf]",
40
+ "high": "[inf inf inf inf inf]",
41
+ "bounded_below": "[False False False False False]",
42
+ "bounded_above": "[False False False False False]",
43
+ "_np_random": "RandomState(MT19937)"
44
+ },
45
+ "action_space": {
46
+ ":type:": "<class 'gym.spaces.box.Box'>",
47
+ ":serialized:": "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",
48
+ "dtype": "float32",
49
+ "_shape": [
50
+ 1
51
+ ],
52
+ "low": "[-1.]",
53
+ "high": "[1.]",
54
+ "bounded_below": "[ True]",
55
+ "bounded_above": "[ True]",
56
+ "_np_random": "RandomState(MT19937)"
57
+ },
58
+ "n_envs": 1,
59
+ "num_timesteps": 1000000,
60
+ "_total_timesteps": 1000000,
61
+ "_num_timesteps_at_start": 0,
62
+ "seed": 0,
63
+ "action_noise": {
64
+ ":type:": "<class 'stable_baselines3.common.noise.OrnsteinUhlenbeckActionNoise'>",
65
+ ":serialized:": "gAWVVQEAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5ub2lzZZSMHE9ybnN0ZWluVWhsZW5iZWNrQWN0aW9uTm9pc2WUk5QpgZR9lCiMBl90aGV0YZRHP8MzMzMzMzOMA19tdZSMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYIAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBhZSMAUOUdJRSlIwGX3NpZ21hlGgJKJYIAAAAAAAAADMzMzMzM9M/lGgQSwGFlGgUdJRSlIwDX2R0lEc/hHrhR64Ue4wNaW5pdGlhbF9ub2lzZZROjApub2lzZV9wcmV2lGgJKJYIAAAAAAAAAAAAAAAAAAAAlGgQSwGFlGgUdJRSlHViLg==",
66
+ "_theta": 0.15,
67
+ "_mu": "[0.]",
68
+ "_sigma": "[0.3]",
69
+ "_dt": 0.01,
70
+ "initial_noise": null,
71
+ "noise_prev": "[0.]"
72
+ },
73
+ "start_time": 1673811020539276343,
74
+ "learning_rate": {
75
+ ":type:": "<class 'function'>",
76
+ ":serialized:": "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"
77
+ },
78
+ "tensorboard_log": "runs/CartpoleSwingupSparseDMC-v0__ddpg__3404852292__1673811016/CartpoleSwingupSparseDMC-v0",
79
+ "lr_schedule": {
80
+ ":type:": "<class 'function'>",
81
+ ":serialized:": "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"
82
+ },
83
+ "_last_obs": null,
84
+ "_last_episode_starts": {
85
+ ":type:": "<class 'numpy.ndarray'>",
86
+ ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
87
+ },
88
+ "_last_original_obs": {
89
+ ":type:": "<class 'numpy.ndarray'>",
90
+ ":serialized:": "gAWViQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYUAAAAAAAAAOjX370u0X8/a80avUViKz9aIWu8lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwWGlIwBQ5R0lFKULg=="
91
+ },
92
+ "_episode_num": 1000,
93
+ "use_sde": false,
94
+ "sde_sample_freq": -1,
95
+ "_current_progress_remaining": 0.0,
96
+ "ep_info_buffer": {
97
+ ":type:": "<class 'collections.deque'>",
98
+ ":serialized:": "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"
99
+ },
100
+ "ep_success_buffer": {
101
+ ":type:": "<class 'collections.deque'>",
102
+ ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
103
+ },
104
+ "_n_updates": 1000000,
105
+ "buffer_size": 1,
106
+ "batch_size": 64,
107
+ "learning_starts": 100,
108
+ "tau": 0.005,
109
+ "gamma": 0.99,
110
+ "gradient_steps": -1,
111
+ "optimize_memory_usage": false,
112
+ "replay_buffer_class": {
113
+ ":type:": "<class 'abc.ABCMeta'>",
114
+ ":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
115
+ "__module__": "stable_baselines3.common.buffers",
116
+ "__doc__": "\n Replay buffer used in off-policy algorithms like SAC/TD3.\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 of the replay buffer which reduces by almost a factor two the memory used,\n at a cost of more complexity.\n See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n Cannot be used in combination with handle_timeout_termination.\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 ",
117
+ "__init__": "<function ReplayBuffer.__init__ at 0x12af96dd0>",
118
+ "add": "<function ReplayBuffer.add at 0x12af96e60>",
119
+ "sample": "<function ReplayBuffer.sample at 0x12af96ef0>",
120
+ "_get_samples": "<function ReplayBuffer._get_samples at 0x12af96f80>",
121
+ "__abstractmethods__": "frozenset()",
122
+ "_abc_impl": "<_abc._abc_data object at 0x12af36500>"
123
+ },
124
+ "replay_buffer_kwargs": {},
125
+ "train_freq": {
126
+ ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
127
+ ":serialized:": "gAWVZAAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMB2VwaXNvZGWUhZRSlIaUgZQu"
128
+ },
129
+ "use_sde_at_warmup": false,
130
+ "policy_delay": 1,
131
+ "target_noise_clip": 0.0,
132
+ "target_policy_noise": 0.1,
133
+ "actor_batch_norm_stats": [],
134
+ "critic_batch_norm_stats": [],
135
+ "actor_batch_norm_stats_target": [],
136
+ "critic_batch_norm_stats_target": []
137
+ }
ddpg-CartpoleSwingupSparseDMC-v0/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11cb1164182fb7bf2ac5e7e7fe455b6f86296a32958e19ea147af318008d874f
3
+ size 1492509
ddpg-CartpoleSwingupSparseDMC-v0/pytorch_variables.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
3
+ size 431
ddpg-CartpoleSwingupSparseDMC-v0/system_info.txt ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ - OS: macOS-13.0.1-arm64-arm-64bit Darwin Kernel Version 22.1.0: Sun Oct 9 20:14:30 PDT 2022; root:xnu-8792.41.9~2/RELEASE_ARM64_T8103
2
+ - Python: 3.10.9
3
+ - Stable-Baselines3: 1.7.0
4
+ - PyTorch: 1.13.1
5
+ - GPU Enabled: False
6
+ - Numpy: 1.24.1
7
+ - Gym: 0.21.0
env_kwargs.yml ADDED
@@ -0,0 +1 @@
 
 
1
+ {}
replay.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fb5bc4cbb02b6687376d3ebea42da7d84d1c342ce7fa31d9f1c84e3b976a307
3
+ size 179832
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": 344.2, "std_reward": 1.661324772583615, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-16T08:52:35.301508"}
train_eval_metrics.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd411587dd5f0b3a32e9d8adaac61845aee8bbfbcece7a9299492f3a6ef0f4ec
3
+ size 37440