Quentin Gallouédec commited on
Commit
b74096c
1 Parent(s): d8c2ce1

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
+ - AcrobotSwingupDMC-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: AcrobotSwingupDMC-v0
16
+ type: AcrobotSwingupDMC-v0
17
+ metrics:
18
+ - type: mean_reward
19
+ value: 96.89 +/- 64.09
20
+ name: mean_reward
21
+ verified: false
22
+ ---
23
+
24
+ # **DDPG** Agent playing **AcrobotSwingupDMC-v0**
25
+ This is a trained model of a **DDPG** agent playing **AcrobotSwingupDMC-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 AcrobotSwingupDMC-v0 -orga qgallouedec -f logs/
47
+ python -m rl_zoo3.enjoy --algo ddpg --env AcrobotSwingupDMC-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 AcrobotSwingupDMC-v0 -orga qgallouedec -f logs/
53
+ python -m rl_zoo3.enjoy --algo ddpg --env AcrobotSwingupDMC-v0 -f logs/
54
+ ```
55
+
56
+ ## Training (with the RL Zoo)
57
+ ```
58
+ python -m rl_zoo3.train --algo ddpg --env AcrobotSwingupDMC-v0 -f logs/
59
+ # Upload the model and generate video (when possible)
60
+ python -m rl_zoo3.push_to_hub --algo ddpg --env AcrobotSwingupDMC-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
+ - AcrobotSwingupDMC-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
+ - 3785955249
58
+ - - storage
59
+ - null
60
+ - - study_name
61
+ - null
62
+ - - tensorboard_log
63
+ - runs/AcrobotSwingupDMC-v0__ddpg__3785955249__1673810878
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-AcrobotSwingupDMC-v0.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53ed8a68377ed3c3db3d85386ca97f5b4a05cf7e5c5c34d66bd452830b3229bc
3
+ size 3021849
ddpg-AcrobotSwingupDMC-v0/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 1.7.0
ddpg-AcrobotSwingupDMC-v0/actor.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:679468e32c743a7eaa4e37c24d6e9225b66463ddb5c101db1bf3641fd4198d46
3
+ size 504751
ddpg-AcrobotSwingupDMC-v0/critic.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd05941ac5fca8239f0ad994f2e9d75afc21b0ffad0eb6fb283259cbc4193bf0
3
+ size 995055
ddpg-AcrobotSwingupDMC-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 0x135f98280>",
8
+ "_build": "<function TD3Policy._build at 0x135f98310>",
9
+ "_get_constructor_parameters": "<function TD3Policy._get_constructor_parameters at 0x135f983a0>",
10
+ "make_actor": "<function TD3Policy.make_actor at 0x135f98430>",
11
+ "make_critic": "<function TD3Policy.make_critic at 0x135f984c0>",
12
+ "forward": "<function TD3Policy.forward at 0x135f98550>",
13
+ "_predict": "<function TD3Policy._predict at 0x135f985e0>",
14
+ "set_training_mode": "<function TD3Policy.set_training_mode at 0x135f98670>",
15
+ "__abstractmethods__": "frozenset()",
16
+ "_abc_impl": "<_abc._abc_data object at 0x135f91fc0>"
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
+ 6
38
+ ],
39
+ "low": "[-inf -inf -inf -inf -inf -inf]",
40
+ "high": "[inf inf inf inf inf inf]",
41
+ "bounded_below": "[False False False False False False]",
42
+ "bounded_above": "[False False False False False False]",
43
+ "_np_random": "RandomState(MT19937)"
44
+ },
45
+ "action_space": {
46
+ ":type:": "<class 'gym.spaces.box.Box'>",
47
+ ":serialized:": "gAWVCgwAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLAYWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWBAAAAAAAAAAAAIC/lGgLSwGFlIwBQ5R0lFKUjARoaWdolGgTKJYEAAAAAAAAAAAAgD+UaAtLAYWUaBZ0lFKUjA1ib3VuZGVkX2JlbG93lGgTKJYBAAAAAAAAAAGUaAiMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLAYWUaBZ0lFKUjA1ib3VuZGVkX2Fib3ZllGgTKJYBAAAAAAAAAAGUaCJLAYWUaBZ0lFKUjApfbnBfcmFuZG9tlIwUbnVtcHkucmFuZG9tLl9waWNrbGWUjBJfX3JhbmRvbXN0YXRlX2N0b3KUk5SMB01UMTk5MzeUaC6MFF9fYml0X2dlbmVyYXRvcl9jdG9ylJOUhpRSlH2UKIwNYml0X2dlbmVyYXRvcpSMB01UMTk5MzeUjAVzdGF0ZZR9lCiMA2tleZRoEyiWwAkAAAAAAAAAAACAU8KznIcDtZNy7Ktb6Oay8s+2gdrVBu9hoTFNoGu1zNkT5hifdJx5L8ilG4DEeQFJng9D5F3gGJOSE1XM1EopZNIIlb400J5EcnoD8K2/CnObez7pYLEG2nUDRQtufdYWausENGaDt/P1pS9p70JjQ7Vc98J3UsxGRDctCIlu0I6ud/sYtoBPe575TzLsEti5jl6FqRnKrj12LWcrQoCexe7HH/UiAV1LzyQPzBlSZERXmHCdCvUSF7XpWt47xP9BzzqxX7aH3TPYWImqos1/ez/JlLdsD0MfMZl9G2CQq7cHHRlM3sj7jroA9c+pGt4l/iAGpRb80HbjwU71ykPTAVp531BXrc2qmIU6z9Fh4TAPx7fZ1kVF+L1Irlou+4Ckky7Ys59nB7KkciTI+N5jlb62ybZt0+ZWgIA6LKLvdx/mTQtB4k1aplT/C7L9/ybKCFn2quN/7YlIkxoH1U0xdabG6rgOrR+SHMmvUwvtKB+19Ibb07mSgVQyjNAvnyADPJf3pkxylZtn7f/OVpWEaWfl6BcLwy0grrEgUK+H+8P8XWMuBginXgwzn3sy4+ZOlr45op6TtuqX0Knz/SySGDlBIK8JqKObzB6fGt+ovJHEM8KlL4veKwkLkuuMWBaex3FBdWskry5qhslxMgnk2thh8DaXmAfbuI8j0SqHMW1kleITi9ekfXx/eSi5hX1GjA/M62Zixuay1H8zH9VjsTRcGacyJ0vh1hNReDFoNsXFbLfLqaIvbLDQjY7T289ZXsupvAxu2GVTbqWst+ckPPzwH7vLikULC+weAKwxarqm+ugAXgyz774meHOsvQYuu18nvrrunjZWDvwaKuYohEwUfSnpotE9XhX99yUTc8sGPQidTfXkzm/t8MWP8it4l4VSEgDLn8GW8t2DAh8EwFa/KOGoZEGjYqZ2IMA70E+F2LqgaZlQLFMONTIx3yuN5F2e1MT4v2wdBRK9R+lGMpxIiNldyOwwxLDBTRDMhd7APidmDwQBnvaIecKFa95btwHkRBEUT5g++/I0DDg685EX4OMO2YtTPqM3PQluS4puEhAQRVukNGSh4gYDgcBPKZl4ThNf+G+E7El9fmWJcP39Sifw6Mn+GEisM1RhHY05XZHUv5W4r8kD2jSLMY+IIL2+LtQrW7it7y28+sEicLoEfYOky9ZJF6l0fR+sXEawf+REH9LvtRJ4yzfxr7KisNpr1axv1ae5CDXS+XTzuOG/BJnHvt8arnY1XWH9SdkCOeok6MI8GBCtjTCxJ5JbpI5J0i0A66mJaRW9LMfP6Cil3/cVRQ9uN2KTtV3o7rJwY4XCnj7DJmqrUwofDDl7Ek0PoN7w0Hh8YHOy8qhPw7V8ALdjZn7eYtjCQIldQvHbM1I73RtCLQvQGFMXUCJ022pGRqTvZX5XWSizqbgX6TJmI6LDF9wcpYealB7cDwelfqdpzHRmyjRbIX9b+w4uj//aDRgP2SgiOAq/D/9/0SbgK/E0FQyclhNVAkbKwXhAxKGczpvJow0mFFUAt/5fT5KAsmQTAt8p0FsrGMDTfk4RzZgqZSm+ihVRS371Tx3twpGA1goo/AIfJh8slJC3hkR1OGCN7LAPGCwbM9rHlKSU4uuhJiff196h9q1kPMld6989MfKLVkvCl7ofCRurPUW46ceJKE951sQD1v8cK0HK1JmuBTCXAelCUCIFNLGk3tMXNVmuuFF3o3xb4V4T1IAYIfBdyEVHhIIZOE/JEY79daQw8njYEtQ6YwZ6kNCBYfrjq2OglITcRdwDmINL42ro6HnbWgLZQ8Ce/EiPVBtWHwhvGUHK1FNONzRzXgT1zKEg+WAigeuK4QVIxdITM4YvUyYvpQJuJd+xGD1no7BYIKXdV4aDlsRnWSMmS+zTyTvC0+TgBMCNpMvdChjaB/XTrMVsm0vgPmCYswn067MTYWfm5oCqqmNciqoRfFL2O2mxFT1VMcKDrxHBdBUhSG5UmAerx86KAEytbsCbn6OOj8Y02VwVynzXd0WJfLioeGMZISM1eneWfTc1mQ6CpdDxJqUmU86/KsBL3Bb0S2NAqFysFJZKxDwLej8xz+xH8IxEHzlkiiNH+2IIq0663FAwi6wg6dgcryDqQ+lNDwn898nylrcYShigDrtrFBNezKx3ZjpkPCnPUeQB4hJUrYCUJy5CyytC/x1UsByKez/aSNEWnlWnzYdJf2PoKL0YfmaR3KpXzi9ax3BHPgk1cdmgdVkqevFJ0DUdTBFQj/mhaKqcaT0rKJLgy/11AhWW4nX7+kAdgR0b1iAseI0TbMDtohBuqqUZfqMfUKsdI8v2aeUd0+IqOjPBFe7TZRC7OUYmf789SRTpw9gst4tzx7tLap8JnFt2keKhqd3vBgqpvlsxvx0DcPC+bo/qIldKiAn5D7TPjeWLzJ1gmpk1mVKOyWOv/ZzlRTfe8yEsMsRcgdPxbOuxLjlOwo1uFh9NjHoOz/xbnI62I49ZzT59GUCNtAL74UqjlRoyXZ5ELEjhTn+F5fYfEkY2TnSsgKO4Wwb/xD41S4mBL7LcUyF76ybV7Yx0L6V2QGoSfyhHFqMQJs/haLPPW18mWJb/UDl90ZN9TEzcdXvZsmCeqzCagC6YDHp3fop+5nAQSnT/Byt2j7z+6cnl/aZh6oKs5xrEMmuzpLFbXNVof9hNmX5E0DQ2M8uBqqeW95p6z8ySnOxURAO28oYWsbVyeYaNlWLZrOtIMZDRjjbecSSwMLlrBhw4mZVht4DgOQxI1+P7sPHZLMf89U+5ctf1rD0r1AXgyXjzOxKvCxWMhrz6Ah19+zal/bAIpw+0V7Pq85PRQO4UeScmMwODR8jcOfILuMmo7xXhemY/JqtOncklEaGapMeGlkiefvQkx9L5EWvLn6stI4zRP4pZXx9iOz17IKJmKOVHgCIAOiheb0bwkjNkItlfYO3LzeLLPuBDNLFg7tQu5NPWy28a4nBsE/gsyEteRvF2ECYFIOJg06dzc77IWw7o+z1Q5APxLg9uvyFniYWNuJyk7rflLCmYcg1gN657CWff8YfPr0ukKOamco94X1nFdyroxHiQlRXaP91DOqMueI1pCasyRQt0jtbWwxdEVyzP3GzUZXBWqa0xXCzwe29cxg2aiwKuuAAVfaCE/Pt1cJXq8wvliF81sMDPMbowd9+uyWuExq/e+2W3wWeV3hVofoiEySjBrJPWVJW9++UocJbC0ppNw5mtHktkZqUk6kVtUgVQ4Cj4udj/bluZzcqWjIvOCJO52M+xcQY808Ei8T/lwwS9TguuzQ3e0KR7hptgNcX1/XhCvAuUaAiMAnU0lImIh5RSlChLA2gMTk5OSv////9K/////0sAdJRiTXAChZRoFnSUUpSMA3Bvc5RNcAJ1jAloYXNfZ2F1c3OUSwCMBWdhdXNzlEcAAAAAAAAAAHVidWIu",
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": 1673810881171603198,
74
+ "learning_rate": {
75
+ ":type:": "<class 'function'>",
76
+ ":serialized:": "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"
77
+ },
78
+ "tensorboard_log": "runs/AcrobotSwingupDMC-v0__ddpg__3785955249__1673810878/AcrobotSwingupDMC-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:": "gAWVjQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYYAAAAAAAAAJH7ez+n13U/lbI0PjfLjj6FycbAILwEQZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsGhpSMAUOUdJRSlC4="
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:": "gAWVRAwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQGHtJAUtZmuMAWyUTegDjAF0lEdAvmJGWpqASXV9lChoBkcAAAAAAAAAAGgHTegDaAhHQL5quBGQSzx1fZQoaAZHQEhpclgMMJBoB03oA2gIR0C+cyuTRplCdX2UKGgGR0AqOMn7YTTOaAdN6ANoCEdAvnufsrupj3V9lChoBkdAXQO+XZ5AyGgHTegDaAhHQL6EF8dgfEJ1fZQoaAZHQFjXdU83dbhoB03oA2gIR0C+jIm2w3YMdX2UKGgGRz+cv/R3NcGDaAdN6ANoCEdAvpT9a5f+j3V9lChoBkdAXBg9eQdS22gHTegDaAhHQL6dZ8lXzUZ1fZQoaAZHQGhhOt4iX6ZoB03oA2gIR0C+pcjtCzC2dX2UKGgGRz+3/Ot4iX6ZaAdN6ANoCEdAvq4+9f1Hv3V9lChoBkdAeJHv99+gDmgHTegDaAhHQL62oZRKpUB1fZQoaAZHQD0FvOyE+PloB03oA2gIR0C+vw+Yx+KCdX2UKGgGR0BTCbM5fdAPaAdN6ANoCEdAvsdMCyQgcXV9lChoBkdAArl3hXKbKGgHTegDaAhHQL7PiYJmdy11fZQoaAZHP7L6guh9LHxoB03oA2gIR0C+18WdupCKdX2UKGgGR0BgCSfWcz68aAdN6ANoCEdAvt/8+qzZ6HV9lChoBkdARPXKB/Zuh2gHTegDaAhHQL7oN2fTTfB1fZQoaAZHP5sg+yJKraNoB03oA2gIR0C+8HBZuAI6dX2UKGgGRz6wxvegte2NaAdN6ANoCEdAvvim8wpOOHV9lChoBkc/5lYSxqwhXGgHTegDaAhHQL8A3z4DcM51fZQoaAZHQGNjs2WIGhVoB03oA2gIR0C/CRekUKzBdX2UKGgGR0BfQ8dDIBBBaAdN6ANoCEdAvxFQeRxLkHV9lChoBkc+0Mb3oLXtjWgHTegDaAhHQL8ZiClabF11fZQoaAZHQF41kE9t/F1oB03oA2gIR0C/IcAMH8jzdX2UKGgGRz/N6eoUBXCCaAdN6ANoCEdAvyn6GvfTC3V9lChoBkdAZsSCnP3SKGgHTegDaAhHQL83bIWgvlF1fZQoaAZHP7WPPszEaVFoB03oA2gIR0C/P6cgdOqOdX2UKGgGR0Ao9+yZ8a4uaAdN6ANoCEdAv0fgzi0fHXV9lChoBkdAYUn3IMjNZGgHTegDaAhHQL9QHLzf7791fZQoaAZHQEJg6STyJ9BoB03oA2gIR0C/WFb9AHE/dX2UKGgGR0BEOPr4WUKRaAdN6ANoCEdAv2CTkili0HV9lChoBkcAAAAAAAAAAGgHTegDaAhHQL9oqOMVDa51fZQoaAZHQBzJGWldkaxoB03oA2gIR0C/cNk+5e7ddX2UKGgGR0BEJI4MnZ00aAdN6ANoCEdAv3jduzhP03V9lChoBkcAAAAAAAAAAGgHTegDaAhHQL+A16jWTX91fZQoaAZHQEEtduYQarFoB03oA2gIR0C/iNNZA6dUdX2UKGgGR0BgM4UWVNYbaAdN6ANoCEdAv5DSCbtqpXV9lChoBkcAAAAAAAAAAGgHTegDaAhHQL+YzavRqoJ1fZQoaAZHQEIRJ3gUDdRoB03oA2gIR0C/oMoWk8A8dX2UKGgGRwAAAAAAAAAAaAdN6ANoCEdAv6jHrAxi5XV9lChoBkdAW4F7NSqEOGgHTegDaAhHQL+wxqW1MM91fZQoaAZHQD91XmvGIbhoB03oA2gIR0C/uMb/bTMJdX2UKGgGR0BTw8jeKsMiaAdN6ANoCEdAv8DFp/PPcHV9lChoBkc/lTOxB3RoiGgHTegDaAhHQL/Iw2fChvl1fZQoaAZHQF7I+z+m3vxoB03oA2gIR0C/0MQbADaHdX2UKGgGRz/phF/hESdwaAdN6ANoCEdAv9jCUxEfDHV9lChoBkdANYEmUnogWGgHTegDaAhHQL/gwn/DLr51fZQoaAZHQGNuhybQTmJoB03oA2gIR0C/6MGexwAEdX2UKGgGR0Bkr2vB7/n4aAdN6ANoCEdAv/DC2JBPbnV9lChoBkdAYQd/rjYI0WgHTegDaAhHQL/4xcophF51fZQoaAZHQFKZKTSsr/doB03oA2gIR0DAAwDKPn0TdX2UKGgGR0A61OoYNy5qaAdN6ANoCEdAwAcBCTlkpnV9lChoBkdAXk1DTjNpumgHTegDaAhHQMALAPitJWh1fZQoaAZHPyDohY/3WWhoB03oA2gIR0DADwGwosqbdX2UKGgGRz+uuHN5dGAkaAdN6ANoCEdAwBMAabWmQHV9lChoBkdAUmdKraM72mgHTegDaAhHQMAW/5rP+n91fZQoaAZHP7BiPQv6CUZoB03oA2gIR0DAGwDlLeyidX2UKGgGR0BU4AkLQXyiaAdN6ANoCEdAwB8Bh8Yyf3V9lChoBkdAGiqTr3TNMWgHTegDaAhHQMAjAfwiJO51fZQoaAZHAAAAAAAAAABoB03oA2gIR0DAJwG5WilBdX2UKGgGRz+N+gDifg76aAdN6ANoCEdAwCsCm2LHdXV9lChoBkdAZo+xi5NGmWgHTegDaAhHQMAvBBxYJVt1fZQoaAZHAAAAAAAAAABoB03oA2gIR0DAMwRBu4wzdX2UKGgGR0AptFAE+xGEaAdN6ANoCEdAwDcElMyrP3V9lChoBkdAVNmzru6VdGgHTegDaAhHQMA7BiYCyQh1fZQoaAZHQBbYYixFAmloB03oA2gIR0DAPwaJ9AoodX2UKGgGRz+50T101ZTyaAdN6ANoCEdAwEMH7VrhznV9lChoBkc/uE9t/FzdUWgHTegDaAhHQMBHBs67ulZ1fZQoaAZHP6mMGX5WRzRoB03oA2gIR0DASwfUrkKedX2UKGgGRz+4/3WWhRIjaAdN6ANoCEdAwE8I8lHBlHV9lChoBkdAJ6EeQuEmIGgHTegDaAhHQMBTCQbMott1fZQoaAZHQDzsGdI5HVhoB03oA2gIR0DAVwlfsu3+dX2UKGgGR0BqqFxp+MIeaAdN6ANoCEdAwFsKE384xXV9lChoBkcAAAAAAAAAAGgHTegDaAhHQMBfDHkT6BR1fZQoaAZHQEy27mMfigloB03oA2gIR0DAYw0/fO2RdX2UKGgGR0BGguTA31jBaAdN6ANoCEdAwGmsBbwBo3V9lChoBkdAaMqCYCyQgmgHTegDaAhHQMBtr4Enssx1fZQoaAZHQGhzaVt4zJpoB03oA2gIR0DAcbCSaEzwdX2UKGgGR0A6bfuCwr1/aAdN6ANoCEdAwHWzguRLb3V9lChoBkdAX9E/JNj9XWgHTegDaAhHQMB5tdbHIZJ1fZQoaAZHQGk/FnqVyFRoB03oA2gIR0DAfbe4PPLQdX2UKGgGRz+ORHPNVzZIaAdN6ANoCEdAwIG5oQnQY3V9lChoBkdAUeWQRwqAjWgHTegDaAhHQMCFupDu0C11fZQoaAZHQCM4tjCpFThoB03oA2gIR0DAibuOjqOcdX2UKGgGR0AlwJcgQpWnaAdN6ANoCEdAwI29yRSxaHV9lChoBkdAMfSm65Gz8mgHTegDaAhHQMCRvyvC/Gl1fZQoaAZHQDvjUMG5c1RoB03oA2gIR0DAlcHMKTjedX2UKGgGRz/4jKDCgsbvaAdN6ANoCEdAwJnDWxQizXV9lChoBkc/LzH0btJFs2gHTegDaAhHQMCdxbhegL91fZQoaAZHP+ErMkhRqGloB03oA2gIR0DAocmYrrgPdX2UKGgGR0BHdsUqQRwqaAdN6ANoCEdAwKXM02LpA3V9lChoBkdAbf6iQkona2gHTegDaAhHQMCpz1YZEUl1fZQoaAZHAAAAAAAAAABoB03oA2gIR0DArdIVj7Q+dX2UKGgGR0BxFlBt1p0waAdN6ANoCEdAwLHURf4REnV9lChoBkdAS8wjUutfX2gHTegDaAhHQMC1101AJLN1fZQoaAZHPtDG96C17Y1oB03oA2gIR0DAudpmdy1edX2UKGgGR0BSTBmK64DtaAdN6ANoCEdAwL3dYaHbh3V9lChoBkdAEgVVghKUV2gHTegDaAhHQMDB4PXTVlR1fZQoaAZHQFS7SowVTJhoB03oA2gIR0DAxeQfKZDzdX2UKGgGR0BFakFwDNhWaAdN6ANoCEdAwMnn2ki2UnVlLg=="
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 0x135f96dd0>",
118
+ "add": "<function ReplayBuffer.add at 0x135f96e60>",
119
+ "sample": "<function ReplayBuffer.sample at 0x135f96ef0>",
120
+ "_get_samples": "<function ReplayBuffer._get_samples at 0x135f96f80>",
121
+ "__abstractmethods__": "frozenset()",
122
+ "_abc_impl": "<_abc._abc_data object at 0x135f3d540>"
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-AcrobotSwingupDMC-v0/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d61fce2e60d29a9b6acad96eacea4580f3bae5b21109e1cb448e53fbf3c2009
3
+ size 1498141
ddpg-AcrobotSwingupDMC-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-AcrobotSwingupDMC-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:df8fdca582abd595a1f0a7f35b5855d686514796c21941c7c2d5ae7075e286aa
3
+ size 263148
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": 96.8920822, "std_reward": 64.0942718002846, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-15T23:06:03.227002"}
train_eval_metrics.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a429e8dd8007a2d2db0018357a8fd3ef3f4d4d1b85929d160e502c29d7d2e491
3
+ size 41331