araffin commited on
Commit
61ea8b8
1 Parent(s): 80fea31

Initial commit

Browse files
.gitattributes CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
28
+ *.mp4 filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: stable-baselines3
3
+ tags:
4
+ - Acrobot-v1
5
+ - deep-reinforcement-learning
6
+ - reinforcement-learning
7
+ - stable-baselines3
8
+ model-index:
9
+ - name: QRDQN
10
+ results:
11
+ - metrics:
12
+ - type: mean_reward
13
+ value: -67.30 +/- 6.97
14
+ name: mean_reward
15
+ task:
16
+ type: reinforcement-learning
17
+ name: reinforcement-learning
18
+ dataset:
19
+ name: Acrobot-v1
20
+ type: Acrobot-v1
21
+ ---
22
+
23
+ # **QRDQN** Agent playing **Acrobot-v1**
24
+ This is a trained model of a **QRDQN** agent playing **Acrobot-v1**
25
+ using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
26
+ and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
27
+
28
+ The RL Zoo is a training framework for Stable Baselines3
29
+ reinforcement learning agents,
30
+ with hyperparameter optimization and pre-trained agents included.
31
+
32
+ ## Usage (with SB3 RL Zoo)
33
+
34
+ RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
35
+ SB3: https://github.com/DLR-RM/stable-baselines3<br/>
36
+ SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
37
+
38
+ ```
39
+ # Download model and save it into the logs/ folder
40
+ python -m utils.load_from_hub --algo qrdqn --env Acrobot-v1 -orga sb3 -f logs/
41
+ python enjoy.py --algo qrdqn --env Acrobot-v1 -f logs/
42
+ ```
43
+
44
+ ## Training (with the RL Zoo)
45
+ ```
46
+ python train.py --algo qrdqn --env Acrobot-v1 -f logs/
47
+ # Upload the model and generate video (when possible)
48
+ python -m utils.push_to_hub --algo qrdqn --env Acrobot-v1 -f logs/ -orga sb3
49
+ ```
50
+
51
+ ## Hyperparameters
52
+ ```python
53
+ OrderedDict([('batch_size', 128),
54
+ ('buffer_size', 50000),
55
+ ('exploration_final_eps', 0.1),
56
+ ('exploration_fraction', 0.12),
57
+ ('gamma', 0.99),
58
+ ('gradient_steps', -1),
59
+ ('learning_rate', 0.00063),
60
+ ('learning_starts', 0),
61
+ ('n_timesteps', 100000.0),
62
+ ('policy', 'MlpPolicy'),
63
+ ('policy_kwargs', 'dict(net_arch=[256, 256], n_quantiles=25)'),
64
+ ('target_update_interval', 250),
65
+ ('train_freq', 4),
66
+ ('normalize', False)])
67
+ ```
args.yml ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - algo
3
+ - qrdqn
4
+ - - env
5
+ - Acrobot-v1
6
+ - - env_kwargs
7
+ - null
8
+ - - eval_episodes
9
+ - 10
10
+ - - eval_freq
11
+ - 10000
12
+ - - gym_packages
13
+ - []
14
+ - - hyperparams
15
+ - null
16
+ - - log_folder
17
+ - rl-trained-agents/
18
+ - - log_interval
19
+ - -1
20
+ - - n_evaluations
21
+ - 20
22
+ - - n_jobs
23
+ - 1
24
+ - - n_startup_trials
25
+ - 10
26
+ - - n_timesteps
27
+ - -1
28
+ - - n_trials
29
+ - 10
30
+ - - num_threads
31
+ - -1
32
+ - - optimize_hyperparameters
33
+ - false
34
+ - - pruner
35
+ - median
36
+ - - sampler
37
+ - tpe
38
+ - - save_freq
39
+ - -1
40
+ - - save_replay_buffer
41
+ - false
42
+ - - seed
43
+ - 1601973299
44
+ - - storage
45
+ - null
46
+ - - study_name
47
+ - null
48
+ - - tensorboard_log
49
+ - ''
50
+ - - trained_agent
51
+ - ''
52
+ - - truncate_last_trajectory
53
+ - true
54
+ - - uuid
55
+ - true
56
+ - - vec_env
57
+ - dummy
58
+ - - verbose
59
+ - 1
config.yml ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - batch_size
3
+ - 128
4
+ - - buffer_size
5
+ - 50000
6
+ - - exploration_final_eps
7
+ - 0.1
8
+ - - exploration_fraction
9
+ - 0.12
10
+ - - gamma
11
+ - 0.99
12
+ - - gradient_steps
13
+ - -1
14
+ - - learning_rate
15
+ - 0.00063
16
+ - - learning_starts
17
+ - 0
18
+ - - n_timesteps
19
+ - 100000.0
20
+ - - policy
21
+ - MlpPolicy
22
+ - - policy_kwargs
23
+ - dict(net_arch=[256, 256], n_quantiles=25)
24
+ - - target_update_interval
25
+ - 250
26
+ - - train_freq
27
+ - 4
env_kwargs.yml ADDED
@@ -0,0 +1 @@
 
 
1
+ {}
qrdqn-Acrobot-v1.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a77f6c028ce956739453795c0383b3a1509537478312d924b21b2b41f3d3678
3
+ size 1417564
qrdqn-Acrobot-v1/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 1.5.1a8
qrdqn-Acrobot-v1/data ADDED
@@ -0,0 +1,129 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "policy_class": {
3
+ ":type:": "<class 'abc.ABCMeta'>",
4
+ ":serialized:": "gASVLgAAAAAAAACMGnNiM19jb250cmliLnFyZHFuLnBvbGljaWVzlIwLUVJEUU5Qb2xpY3mUk5Qu",
5
+ "__module__": "sb3_contrib.qrdqn.policies",
6
+ "__doc__": "\n Policy class with quantile and target networks for QR-DQN.\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 n_quantiles: Number of quantiles\n :param net_arch: The specification of the network architecture.\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 ",
7
+ "__init__": "<function QRDQNPolicy.__init__ at 0x7f9ecc75a9e0>",
8
+ "_build": "<function QRDQNPolicy._build at 0x7f9ecc75aa70>",
9
+ "make_quantile_net": "<function QRDQNPolicy.make_quantile_net at 0x7f9ecc75ab00>",
10
+ "forward": "<function QRDQNPolicy.forward at 0x7f9ecc75ab90>",
11
+ "_predict": "<function QRDQNPolicy._predict at 0x7f9ecc75ac20>",
12
+ "_get_constructor_parameters": "<function QRDQNPolicy._get_constructor_parameters at 0x7f9ecc75acb0>",
13
+ "set_training_mode": "<function QRDQNPolicy.set_training_mode at 0x7f9ecc75ad40>",
14
+ "__abstractmethods__": "frozenset()",
15
+ "_abc_impl": "<_abc_data object at 0x7f9ecc7a9fc0>"
16
+ },
17
+ "verbose": 1,
18
+ "policy_kwargs": {
19
+ ":type:": "<class 'dict'>",
20
+ ":serialized:": "gASVfQAAAAAAAAB9lCiMCG5ldF9hcmNolF2UKE0AAU0AAWWMC25fcXVhbnRpbGVzlEsZjA9vcHRpbWl6ZXJfY2xhc3OUjBB0b3JjaC5vcHRpbS5hZGFtlIwEQWRhbZSTlIwQb3B0aW1pemVyX2t3YXJnc5R9lIwDZXBzlEc/FHrhR64Ue3N1Lg==",
21
+ "net_arch": [
22
+ 256,
23
+ 256
24
+ ],
25
+ "n_quantiles": 25,
26
+ "optimizer_class": "<class 'torch.optim.adam.Adam'>",
27
+ "optimizer_kwargs": {
28
+ "eps": 7.8125e-05
29
+ }
30
+ },
31
+ "observation_space": {
32
+ ":type:": "<class 'gym.spaces.box.Box'>",
33
+ ":serialized:": "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",
34
+ "dtype": "float32",
35
+ "low": "[ -1. -1. -1. -1. -12.566371 -28.274334]",
36
+ "high": "[ 1. 1. 1. 1. 12.566371 28.274334]",
37
+ "bounded_below": "[ True True True True True True]",
38
+ "bounded_above": "[ True True True True True True]",
39
+ "_np_random": null,
40
+ "_shape": [
41
+ 6
42
+ ]
43
+ },
44
+ "action_space": {
45
+ ":type:": "<class 'gym.spaces.discrete.Discrete'>",
46
+ ":serialized:": "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",
47
+ "n": 3,
48
+ "dtype": "int64",
49
+ "_np_random": "RandomState(MT19937)",
50
+ "_shape": []
51
+ },
52
+ "n_envs": 1,
53
+ "num_timesteps": 100000,
54
+ "_total_timesteps": 100000,
55
+ "_num_timesteps_at_start": 0,
56
+ "seed": 0,
57
+ "action_noise": null,
58
+ "start_time": 1614621647.0116935,
59
+ "learning_rate": {
60
+ ":type:": "<class 'function'>",
61
+ ":serialized:": "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"
62
+ },
63
+ "tensorboard_log": null,
64
+ "lr_schedule": {
65
+ ":type:": "<class 'function'>",
66
+ ":serialized:": "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"
67
+ },
68
+ "_last_obs": null,
69
+ "_last_episode_starts": null,
70
+ "_last_original_obs": {
71
+ ":type:": "<class 'numpy.ndarray'>",
72
+ ":serialized:": "gASVogAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwFLBoaUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUMY0S8RPu5pfb/jqJm+9TJ0P+ioZr+RsVlAlHSUYi4="
73
+ },
74
+ "_episode_num": 1000,
75
+ "use_sde": false,
76
+ "sde_sample_freq": -1,
77
+ "_current_progress_remaining": 0.0,
78
+ "ep_info_buffer": {
79
+ ":type:": "<class 'collections.deque'>",
80
+ ":serialized:": "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"
81
+ },
82
+ "ep_success_buffer": {
83
+ ":type:": "<class 'collections.deque'>",
84
+ ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
85
+ },
86
+ "_n_updates": 100000,
87
+ "buffer_size": 1,
88
+ "batch_size": 128,
89
+ "learning_starts": 0,
90
+ "tau": 1.0,
91
+ "gamma": 0.99,
92
+ "gradient_steps": -1,
93
+ "optimize_memory_usage": false,
94
+ "replay_buffer_class": {
95
+ ":type:": "<class 'abc.ABCMeta'>",
96
+ ":serialized:": "gASVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
97
+ "__module__": "stable_baselines3.common.buffers",
98
+ "__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:\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 :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 ",
99
+ "__init__": "<function ReplayBuffer.__init__ at 0x7f9eccf43b90>",
100
+ "add": "<function ReplayBuffer.add at 0x7f9eccf43c20>",
101
+ "sample": "<function ReplayBuffer.sample at 0x7f9eccaaa7a0>",
102
+ "_get_samples": "<function ReplayBuffer._get_samples at 0x7f9eccaaa830>",
103
+ "__abstractmethods__": "frozenset()",
104
+ "_abc_impl": "<_abc_data object at 0x7f9eccf9a5d0>"
105
+ },
106
+ "replay_buffer_kwargs": {},
107
+ "train_freq": {
108
+ ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
109
+ ":serialized:": "gASVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLBGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
110
+ },
111
+ "actor": null,
112
+ "use_sde_at_warmup": false,
113
+ "exploration_initial_eps": 1.0,
114
+ "exploration_final_eps": 0.1,
115
+ "exploration_fraction": 0.12,
116
+ "target_update_interval": 250,
117
+ "max_grad_norm": null,
118
+ "exploration_rate": 0.1,
119
+ "exploration_schedule": {
120
+ ":type:": "<class 'function'>",
121
+ ":serialized:": "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"
122
+ },
123
+ "_last_dones": {
124
+ ":type:": "<class 'numpy.ndarray'>",
125
+ ":serialized:": "gASViQAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwGFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDAQCUdJRiLg=="
126
+ },
127
+ "remove_time_limit_termination": false,
128
+ "n_quantiles": 25
129
+ }
qrdqn-Acrobot-v1/policy.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf700ccafcdd0ec0be9d1c4aa17c0152002884554e09ac0c6d91ac85267b9079
3
+ size 698177
qrdqn-Acrobot-v1/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9370f46c33f5b318334f800af5d550b16f5ef910b1e561506d331c39e1d44b47
3
+ size 699265
qrdqn-Acrobot-v1/pytorch_variables.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
3
+ size 431
qrdqn-Acrobot-v1/system_info.txt ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ OS: Linux-5.13.0-44-generic-x86_64-with-debian-bullseye-sid #49~20.04.1-Ubuntu SMP Wed May 18 18:44:28 UTC 2022
2
+ Python: 3.7.10
3
+ Stable-Baselines3: 1.5.1a8
4
+ PyTorch: 1.11.0
5
+ GPU Enabled: True
6
+ Numpy: 1.21.2
7
+ Gym: 0.21.0
replay.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eb3e63526be2f9b723b0e3757c3d9fc76bcfad2112d126046315049bdea0258
3
+ size 927097
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": -67.3, "std_reward": 6.972087205421343, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T16:37:24.713677"}
train_eval_metrics.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:072e524715ec1a6d19e0b450d2cbd75921dcdfa04f60388592d15b6aa5376e1b
3
+ size 24123