jackoyoungblood commited on
Commit
df709d7
1 Parent(s): 33d41e6

Initial commit

Browse files
.gitattributes CHANGED
@@ -29,3 +29,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
29
  *.zip filter=lfs diff=lfs merge=lfs -text
30
  *.zst filter=lfs diff=lfs merge=lfs -text
31
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
29
  *.zip filter=lfs diff=lfs merge=lfs -text
30
  *.zst filter=lfs diff=lfs merge=lfs -text
31
  *tfevents* filter=lfs diff=lfs merge=lfs -text
32
+ *.mp4 filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: stable-baselines3
3
+ tags:
4
+ - CartPole-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: 500.00 +/- 0.00
14
+ name: mean_reward
15
+ task:
16
+ type: reinforcement-learning
17
+ name: reinforcement-learning
18
+ dataset:
19
+ name: CartPole-v1
20
+ type: CartPole-v1
21
+ ---
22
+
23
+ # **QRDQN** Agent playing **CartPole-v1**
24
+ This is a trained model of a **QRDQN** agent playing **CartPole-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 CartPole-v1 -orga jackoyoungblood -f logs/
41
+ python enjoy.py --algo qrdqn --env CartPole-v1 -f logs/
42
+ ```
43
+
44
+ ## Training (with the RL Zoo)
45
+ ```
46
+ python train.py --algo qrdqn --env CartPole-v1 -f logs/
47
+ # Upload the model and generate video (when possible)
48
+ python -m utils.push_to_hub --algo qrdqn --env CartPole-v1 -f logs/ -orga jackoyoungblood
49
+ ```
50
+
51
+ ## Hyperparameters
52
+ ```python
53
+ OrderedDict([('batch_size', 64),
54
+ ('buffer_size', 100000),
55
+ ('exploration_final_eps', 0.04),
56
+ ('exploration_fraction', 0.16),
57
+ ('gamma', 0.99),
58
+ ('gradient_steps', 128),
59
+ ('learning_rate', 0.0023),
60
+ ('learning_starts', 1000),
61
+ ('n_timesteps', 50000.0),
62
+ ('policy', 'MlpPolicy'),
63
+ ('policy_kwargs', 'dict(net_arch=[256, 256], n_quantiles=10)'),
64
+ ('target_update_interval', 10),
65
+ ('train_freq', 256),
66
+ ('normalize', False)])
67
+ ```
args.yml ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - algo
3
+ - qrdqn
4
+ - - device
5
+ - auto
6
+ - - env
7
+ - CartPole-v1
8
+ - - env_kwargs
9
+ - null
10
+ - - eval_episodes
11
+ - 5
12
+ - - eval_freq
13
+ - 25000
14
+ - - gym_packages
15
+ - []
16
+ - - hyperparams
17
+ - null
18
+ - - log_folder
19
+ - logs/
20
+ - - log_interval
21
+ - -1
22
+ - - max_total_trials
23
+ - null
24
+ - - n_eval_envs
25
+ - 1
26
+ - - n_evaluations
27
+ - null
28
+ - - n_jobs
29
+ - 1
30
+ - - n_startup_trials
31
+ - 10
32
+ - - n_timesteps
33
+ - -1
34
+ - - n_trials
35
+ - 500
36
+ - - no_optim_plots
37
+ - false
38
+ - - num_threads
39
+ - -1
40
+ - - optimization_log_path
41
+ - null
42
+ - - optimize_hyperparameters
43
+ - false
44
+ - - pruner
45
+ - median
46
+ - - sampler
47
+ - tpe
48
+ - - save_freq
49
+ - -1
50
+ - - save_replay_buffer
51
+ - false
52
+ - - seed
53
+ - 954031387
54
+ - - storage
55
+ - null
56
+ - - study_name
57
+ - null
58
+ - - tensorboard_log
59
+ - ''
60
+ - - track
61
+ - false
62
+ - - trained_agent
63
+ - ''
64
+ - - truncate_last_trajectory
65
+ - true
66
+ - - uuid
67
+ - false
68
+ - - vec_env
69
+ - dummy
70
+ - - verbose
71
+ - 1
72
+ - - wandb_entity
73
+ - null
74
+ - - wandb_project_name
75
+ - sb3
config.yml ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - batch_size
3
+ - 64
4
+ - - buffer_size
5
+ - 100000
6
+ - - exploration_final_eps
7
+ - 0.04
8
+ - - exploration_fraction
9
+ - 0.16
10
+ - - gamma
11
+ - 0.99
12
+ - - gradient_steps
13
+ - 128
14
+ - - learning_rate
15
+ - 0.0023
16
+ - - learning_starts
17
+ - 1000
18
+ - - n_timesteps
19
+ - 50000.0
20
+ - - policy
21
+ - MlpPolicy
22
+ - - policy_kwargs
23
+ - dict(net_arch=[256, 256], n_quantiles=10)
24
+ - - target_update_interval
25
+ - 10
26
+ - - train_freq
27
+ - 256
env_kwargs.yml ADDED
@@ -0,0 +1 @@
 
 
1
+ {}
qrdqn-CartPole-v1.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db4ad370ad82252ed7587db7eedd4a7dcb9298d5e75b648ddcb98d100f31e3f1
3
+ size 1184899
qrdqn-CartPole-v1/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 1.6.0
qrdqn-CartPole-v1/data ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 0x7fc6de66dc20>",
8
+ "_build": "<function QRDQNPolicy._build at 0x7fc6de66dcb0>",
9
+ "make_quantile_net": "<function QRDQNPolicy.make_quantile_net at 0x7fc6de66dd40>",
10
+ "forward": "<function QRDQNPolicy.forward at 0x7fc6de66ddd0>",
11
+ "_predict": "<function QRDQNPolicy._predict at 0x7fc6de66de60>",
12
+ "_get_constructor_parameters": "<function QRDQNPolicy._get_constructor_parameters at 0x7fc6de66def0>",
13
+ "set_training_mode": "<function QRDQNPolicy.set_training_mode at 0x7fc6de66df80>",
14
+ "__abstractmethods__": "frozenset()",
15
+ "_abc_impl": "<_abc_data object at 0x7fc6de66c1b0>"
16
+ },
17
+ "verbose": 1,
18
+ "policy_kwargs": {
19
+ ":type:": "<class 'dict'>",
20
+ ":serialized:": "gASVfQAAAAAAAAB9lCiMCG5ldF9hcmNolF2UKE0AAU0AAWWMC25fcXVhbnRpbGVzlEsKjA9vcHRpbWl6ZXJfY2xhc3OUjBB0b3JjaC5vcHRpbS5hZGFtlIwEQWRhbZSTlIwQb3B0aW1pemVyX2t3YXJnc5R9lIwDZXBzlEc/JHrhR64Ue3N1Lg==",
21
+ "net_arch": [
22
+ 256,
23
+ 256
24
+ ],
25
+ "n_quantiles": 10,
26
+ "optimizer_class": "<class 'torch.optim.adam.Adam'>",
27
+ "optimizer_kwargs": {
28
+ "eps": 0.00015625
29
+ }
30
+ },
31
+ "observation_space": {
32
+ ":type:": "<class 'gym.spaces.box.Box'>",
33
+ ":serialized:": "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",
34
+ "dtype": "float32",
35
+ "_shape": [
36
+ 4
37
+ ],
38
+ "low": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]",
39
+ "high": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]",
40
+ "bounded_below": "[ True True True True]",
41
+ "bounded_above": "[ True True True True]",
42
+ "_np_random": null
43
+ },
44
+ "action_space": {
45
+ ":type:": "<class 'gym.spaces.discrete.Discrete'>",
46
+ ":serialized:": "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",
47
+ "n": 2,
48
+ "_shape": [],
49
+ "dtype": "int64",
50
+ "_np_random": "RandomState(MT19937)"
51
+ },
52
+ "n_envs": 1,
53
+ "num_timesteps": 50176,
54
+ "_total_timesteps": 50000,
55
+ "_num_timesteps_at_start": 0,
56
+ "seed": 0,
57
+ "action_noise": null,
58
+ "start_time": 1660940826.4835405,
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": {
70
+ ":type:": "<class 'numpy.ndarray'>",
71
+ ":serialized:": "gASViQAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwGFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDAQGUdJRiLg=="
72
+ },
73
+ "_last_original_obs": {
74
+ ":type:": "<class 'numpy.ndarray'>",
75
+ ":serialized:": "gASVmgAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwFLBIaUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUMQABwHP0n5Z74cmd02VAuePpR0lGIu"
76
+ },
77
+ "_episode_num": 329,
78
+ "use_sde": false,
79
+ "sde_sample_freq": -1,
80
+ "_current_progress_remaining": -0.0035199999999999676,
81
+ "ep_info_buffer": {
82
+ ":type:": "<class 'collections.deque'>",
83
+ ":serialized:": "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"
84
+ },
85
+ "ep_success_buffer": {
86
+ ":type:": "<class 'collections.deque'>",
87
+ ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
88
+ },
89
+ "_n_updates": 24704,
90
+ "buffer_size": 1,
91
+ "batch_size": 64,
92
+ "learning_starts": 1000,
93
+ "tau": 1.0,
94
+ "gamma": 0.99,
95
+ "gradient_steps": 128,
96
+ "optimize_memory_usage": false,
97
+ "replay_buffer_class": {
98
+ ":type:": "<class 'abc.ABCMeta'>",
99
+ ":serialized:": "gASVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
100
+ "__module__": "stable_baselines3.common.buffers",
101
+ "__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 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 ",
102
+ "__init__": "<function ReplayBuffer.__init__ at 0x7fc6deec47a0>",
103
+ "add": "<function ReplayBuffer.add at 0x7fc6deec4830>",
104
+ "sample": "<function ReplayBuffer.sample at 0x7fc6deeb1830>",
105
+ "_get_samples": "<function ReplayBuffer._get_samples at 0x7fc6deeb18c0>",
106
+ "__abstractmethods__": "frozenset()",
107
+ "_abc_impl": "<_abc_data object at 0x7fc6def2c060>"
108
+ },
109
+ "replay_buffer_kwargs": {},
110
+ "train_freq": {
111
+ ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
112
+ ":serialized:": "gASVYgAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RNAAFoAIwSVHJhaW5GcmVxdWVuY3lVbml0lJOUjARzdGVwlIWUUpSGlIGULg=="
113
+ },
114
+ "actor": null,
115
+ "use_sde_at_warmup": false,
116
+ "exploration_initial_eps": 1.0,
117
+ "exploration_final_eps": 0.04,
118
+ "exploration_fraction": 0.16,
119
+ "target_update_interval": 10,
120
+ "max_grad_norm": null,
121
+ "exploration_rate": 0.04,
122
+ "exploration_schedule": {
123
+ ":type:": "<class 'function'>",
124
+ ":serialized:": "gASVZQMAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsBSwRLE0MsZAF8ABgAiAFrBHIQiABTAIgCZAF8ABgAiACIAhgAFACIARsAFwBTAGQAUwCUTksBhpQpjBJwcm9ncmVzc19yZW1haW5pbmeUhZSMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuNy9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS25DBgABDAEEApSMA2VuZJSMDGVuZF9mcmFjdGlvbpSMBXN0YXJ0lIeUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuNy9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlGgdKVKUaB0pUpSHlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoI32UfZQoaBhoDYwMX19xdWFsbmFtZV9flIwbZ2V0X2xpbmVhcl9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UKGgKjAhidWlsdGluc5SMBWZsb2F0lJOUjAZyZXR1cm6UaC91jA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoGYwHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/pHrhR64Ue4WUUpRoN0c/xHrhR64Ue4WUUpRoN0c/8AAAAAAAAIWUUpSHlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="
125
+ },
126
+ "n_quantiles": 10
127
+ }
qrdqn-CartPole-v1/policy.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1c9cfd0bc1fb39a0d735743a13786de57552e69afb8985120d910888c86f455
3
+ size 582703
qrdqn-CartPole-v1/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd0f70f89722c8f13cace188dc22bcefa3db7aca1405455ad1ff0f4617b17f42
3
+ size 582145
qrdqn-CartPole-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-CartPole-v1/system_info.txt ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ OS: Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022
2
+ Python: 3.7.13
3
+ Stable-Baselines3: 1.6.0
4
+ PyTorch: 1.12.1+cu113
5
+ GPU Enabled: True
6
+ Numpy: 1.21.6
7
+ Gym: 0.21.0
replay.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5899f808360727250caae83207d3c8040dc1d274685a68b71bd844c916eef8bd
3
+ size 97148
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": 500.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-08-19T20:33:08.288855"}
train_eval_metrics.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6c0122d1e420041d390b18f6110986173c4dd19445396ffe0ba7cfda9de70e5
3
+ size 7624