Quentin Gallouédec commited on
Commit
20b9c5c
1 Parent(s): d20ef22

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 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: DQN
10
+ results:
11
+ - task:
12
+ type: reinforcement-learning
13
+ name: reinforcement-learning
14
+ dataset:
15
+ name: Acrobot-v1
16
+ type: Acrobot-v1
17
+ metrics:
18
+ - type: mean_reward
19
+ value: -86.70 +/- 24.26
20
+ name: mean_reward
21
+ verified: false
22
+ ---
23
+
24
+ # **DQN** Agent playing **Acrobot-v1**
25
+ This is a trained model of a **DQN** agent playing **Acrobot-v1**
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 dqn --env Acrobot-v1 -orga qgallouedec -f logs/
47
+ python -m rl_zoo3.enjoy --algo dqn --env Acrobot-v1 -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 dqn --env Acrobot-v1 -orga qgallouedec -f logs/
53
+ python -m rl_zoo3.enjoy --algo dqn --env Acrobot-v1 -f logs/
54
+ ```
55
+
56
+ ## Training (with the RL Zoo)
57
+ ```
58
+ python -m rl_zoo3.train --algo dqn --env Acrobot-v1 -f logs/
59
+ # Upload the model and generate video (when possible)
60
+ python -m rl_zoo3.push_to_hub --algo dqn --env Acrobot-v1 -f logs/ -orga qgallouedec
61
+ ```
62
+
63
+ ## Hyperparameters
64
+ ```python
65
+ OrderedDict([('batch_size', 128),
66
+ ('buffer_size', 50000),
67
+ ('exploration_final_eps', 0.1),
68
+ ('exploration_fraction', 0.12),
69
+ ('gamma', 0.99),
70
+ ('gradient_steps', -1),
71
+ ('learning_rate', 0.00063),
72
+ ('learning_starts', 0),
73
+ ('n_timesteps', 100000.0),
74
+ ('policy', 'MlpPolicy'),
75
+ ('policy_kwargs', 'dict(net_arch=[256, 256])'),
76
+ ('target_update_interval', 250),
77
+ ('train_freq', 4),
78
+ ('normalize', False)])
79
+ ```
args.yml ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - algo
3
+ - dqn
4
+ - - conf_file
5
+ - null
6
+ - - device
7
+ - auto
8
+ - - env
9
+ - Acrobot-v1
10
+ - - env_kwargs
11
+ - null
12
+ - - eval_episodes
13
+ - 5
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
+ - 1
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
+ - 1186815141
58
+ - - storage
59
+ - null
60
+ - - study_name
61
+ - null
62
+ - - tensorboard_log
63
+ - runs/Acrobot-v1__dqn__1186815141__1671833757
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
+ - openrlbenchmark
78
+ - - wandb_project_name
79
+ - sb3
80
+ - - yaml_file
81
+ - null
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])
24
+ - - target_update_interval
25
+ - 250
26
+ - - train_freq
27
+ - 4
dqn-Acrobot-v1.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b03f1563977bdf5cf467e0f1933cc6a4f1511523b41d0761b650826c7505c309
3
+ size 1122741
dqn-Acrobot-v1/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 1.8.0a6
dqn-Acrobot-v1/data ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "policy_class": {
3
+ ":type:": "<class 'abc.ABCMeta'>",
4
+ ":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmRxbi5wb2xpY2llc5SMCURRTlBvbGljeZSTlC4=",
5
+ "__module__": "stable_baselines3.dqn.policies",
6
+ "__doc__": "\n Policy class with Q-Value Net and target net for 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 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 ",
7
+ "__init__": "<function DQNPolicy.__init__ at 0x7f3803ecb4c0>",
8
+ "_build": "<function DQNPolicy._build at 0x7f3803ecb550>",
9
+ "make_q_net": "<function DQNPolicy.make_q_net at 0x7f3803ecb5e0>",
10
+ "forward": "<function DQNPolicy.forward at 0x7f3803ecb670>",
11
+ "_predict": "<function DQNPolicy._predict at 0x7f3803ecb700>",
12
+ "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x7f3803ecb790>",
13
+ "set_training_mode": "<function DQNPolicy.set_training_mode at 0x7f3803ecb820>",
14
+ "__abstractmethods__": "frozenset()",
15
+ "_abc_impl": "<_abc._abc_data object at 0x7f3803ece500>"
16
+ },
17
+ "verbose": 1,
18
+ "policy_kwargs": {
19
+ "net_arch": [
20
+ 256,
21
+ 256
22
+ ]
23
+ },
24
+ "observation_space": {
25
+ ":type:": "<class 'gym.spaces.box.Box'>",
26
+ ":serialized:": "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",
27
+ "dtype": "float32",
28
+ "_shape": [
29
+ 6
30
+ ],
31
+ "low": "[ -1. -1. -1. -1. -12.566371 -28.274334]",
32
+ "high": "[ 1. 1. 1. 1. 12.566371 28.274334]",
33
+ "bounded_below": "[ True True True True True True]",
34
+ "bounded_above": "[ True True True True True True]",
35
+ "_np_random": null
36
+ },
37
+ "action_space": {
38
+ ":type:": "<class 'gym.spaces.discrete.Discrete'>",
39
+ ":serialized:": "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",
40
+ "n": 3,
41
+ "_shape": [],
42
+ "dtype": "int64",
43
+ "_np_random": "RandomState(MT19937)"
44
+ },
45
+ "n_envs": 1,
46
+ "num_timesteps": 100000,
47
+ "_total_timesteps": 100000,
48
+ "_num_timesteps_at_start": 0,
49
+ "seed": 0,
50
+ "action_noise": null,
51
+ "start_time": 1671833759701185109,
52
+ "learning_rate": {
53
+ ":type:": "<class 'function'>",
54
+ ":serialized:": "gAWVvQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMRS9ob21lL3FnYWxsb3VlZGVjL3N0YWJsZS1iYXNlbGluZXMzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4BDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMRS9ob21lL3FnYWxsb3VlZGVjL3N0YWJsZS1iYXNlbGluZXMzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/RKTSsr/bTYWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="
55
+ },
56
+ "tensorboard_log": "runs/Acrobot-v1__dqn__1186815141__1671833757/Acrobot-v1",
57
+ "lr_schedule": {
58
+ ":type:": "<class 'function'>",
59
+ ":serialized:": "gAWVvQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMRS9ob21lL3FnYWxsb3VlZGVjL3N0YWJsZS1iYXNlbGluZXMzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4BDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMRS9ob21lL3FnYWxsb3VlZGVjL3N0YWJsZS1iYXNlbGluZXMzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/RKTSsr/bTYWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="
60
+ },
61
+ "_last_obs": null,
62
+ "_last_episode_starts": {
63
+ ":type:": "<class 'numpy.ndarray'>",
64
+ ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
65
+ },
66
+ "_last_original_obs": {
67
+ ":type:": "<class 'numpy.ndarray'>",
68
+ ":serialized:": "gAWVjQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYYAAAAAAAAADzGfj8oKsi93o1/P+ugcT05piK/MBi+P5SMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsGhpSMAUOUdJRSlC4="
69
+ },
70
+ "_episode_num": 957,
71
+ "use_sde": false,
72
+ "sde_sample_freq": -1,
73
+ "_current_progress_remaining": 0.0,
74
+ "ep_info_buffer": {
75
+ ":type:": "<class 'collections.deque'>",
76
+ ":serialized:": "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"
77
+ },
78
+ "ep_success_buffer": {
79
+ ":type:": "<class 'collections.deque'>",
80
+ ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
81
+ },
82
+ "_n_updates": 100000,
83
+ "buffer_size": 1,
84
+ "batch_size": 128,
85
+ "learning_starts": 0,
86
+ "tau": 1.0,
87
+ "gamma": 0.99,
88
+ "gradient_steps": -1,
89
+ "optimize_memory_usage": false,
90
+ "replay_buffer_class": {
91
+ ":type:": "<class 'abc.ABCMeta'>",
92
+ ":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
93
+ "__module__": "stable_baselines3.common.buffers",
94
+ "__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 ",
95
+ "__init__": "<function ReplayBuffer.__init__ at 0x7f3803f2a430>",
96
+ "add": "<function ReplayBuffer.add at 0x7f3803f2a4c0>",
97
+ "sample": "<function ReplayBuffer.sample at 0x7f3803f2a550>",
98
+ "_get_samples": "<function ReplayBuffer._get_samples at 0x7f3803f2a5e0>",
99
+ "__abstractmethods__": "frozenset()",
100
+ "_abc_impl": "<_abc._abc_data object at 0x7f38043b3680>"
101
+ },
102
+ "replay_buffer_kwargs": {},
103
+ "train_freq": {
104
+ ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
105
+ ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLBGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
106
+ },
107
+ "actor": null,
108
+ "use_sde_at_warmup": false,
109
+ "exploration_initial_eps": 1.0,
110
+ "exploration_final_eps": 0.1,
111
+ "exploration_fraction": 0.12,
112
+ "target_update_interval": 250,
113
+ "_n_calls": 100000,
114
+ "max_grad_norm": 10,
115
+ "exploration_rate": 0.1,
116
+ "exploration_schedule": {
117
+ ":type:": "<class 'function'>",
118
+ ":serialized:": "gAWVYQMAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLBEsTQyxkAXwAGACIAWsEchCIAFMAiAJkAXwAGACIAIgCGAAUAIgBGwAXAFMAZABTAJROSwGGlCmMEnByb2dyZXNzX3JlbWFpbmluZ5SFlIxFL2hvbWUvcWdhbGxvdWVkZWMvc3RhYmxlLWJhc2VsaW5lczMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLcEMGAAEMAQQClIwDZW5klIwMZW5kX2ZyYWN0aW9ulIwFc3RhcnSUh5QpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxFL2hvbWUvcWdhbGxvdWVkZWMvc3RhYmxlLWJhc2VsaW5lczMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUaB0pUpRoHSlSlIeUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgjfZR9lChoGGgNjAxfX3F1YWxuYW1lX1+UjBtnZXRfbGluZWFyX2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZQoaAqMCGJ1aWx0aW5zlIwFZmxvYXSUk5SMBnJldHVybpRoL3WMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgZjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz+5mZmZmZmahZRSlGg3Rz++uFHrhR64hZRSlGg3Rz/wAAAAAAAAhZRSlIeUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
119
+ },
120
+ "_action_repeat": [
121
+ null
122
+ ],
123
+ "surgeon": null,
124
+ "batch_norm_stats": [],
125
+ "batch_norm_stats_target": [],
126
+ "_last_action": {
127
+ ":type:": "<class 'numpy.ndarray'>",
128
+ ":serialized:": "gAWVewAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYIAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBhZSMAUOUdJRSlC4="
129
+ }
130
+ }
dqn-Acrobot-v1/policy.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfcfd33dc30443e14a1eeb8a7de27ab131d5f114f646581fe5726a16d026f4f0
3
+ size 551855
dqn-Acrobot-v1/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86e6781d4362a39ae15996eb2894382b7d468a0b15d73a1b49dfb99b9353cbc9
3
+ size 550913
dqn-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
dqn-Acrobot-v1/system_info.txt ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ - OS: Linux-5.19.0-32-generic-x86_64-with-glibc2.35 # 33~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Mon Jan 30 17:03:34 UTC 2
2
+ - Python: 3.9.12
3
+ - Stable-Baselines3: 1.8.0a6
4
+ - PyTorch: 1.13.1+cu117
5
+ - GPU Enabled: True
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 sha256:87a68d7ca6925a1b0ca098d8c80972f6dffade20d4eba895d805031b08514c86
3
+ size 951333
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": -86.7, "std_reward": 24.25716389028198, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T16:06:06.810020"}
train_eval_metrics.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f488637cdbf610adeaef07c2a6a86a68229d213d713df7c8d680d0e9d122a9b
3
+ size 21650