Corianas commited on
Commit
dc01ead
1 Parent(s): 3fa2178

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 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: stable-baselines3
3
+ tags:
4
+ - BeamRiderNoFrameskip-v4
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: 13335.00 +/- 5701.88
14
+ name: mean_reward
15
+ task:
16
+ type: reinforcement-learning
17
+ name: reinforcement-learning
18
+ dataset:
19
+ name: BeamRiderNoFrameskip-v4
20
+ type: BeamRiderNoFrameskip-v4
21
+ ---
22
+
23
+ # **QRDQN** Agent playing **BeamRiderNoFrameskip-v4**
24
+ This is a trained model of a **QRDQN** agent playing **BeamRiderNoFrameskip-v4**
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 BeamRiderNoFrameskip-v4 -orga Corianas -f logs/
41
+ python enjoy.py --algo qrdqn --env BeamRiderNoFrameskip-v4 -f logs/
42
+ ```
43
+
44
+ ## Training (with the RL Zoo)
45
+ ```
46
+ python train.py --algo qrdqn --env BeamRiderNoFrameskip-v4 -f logs/
47
+ # Upload the model and generate video (when possible)
48
+ python -m utils.push_to_hub --algo qrdqn --env BeamRiderNoFrameskip-v4 -f logs/ -orga Corianas
49
+ ```
50
+
51
+ ## Hyperparameters
52
+ ```python
53
+ OrderedDict([('env_wrapper',
54
+ ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
55
+ ('exploration_fraction', 0.025),
56
+ ('frame_stack', 3),
57
+ ('n_timesteps', 10000000.0),
58
+ ('optimize_memory_usage', True),
59
+ ('policy', 'CnnPolicy'),
60
+ ('normalize', False)])
61
+ ```
args.yml ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - algo
3
+ - qrdqn
4
+ - - device
5
+ - auto
6
+ - - env
7
+ - BeamRiderNoFrameskip-v4
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
+ - /content/drive/MyDrive/ML
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
+ - 500000
50
+ - - save_replay_buffer
51
+ - false
52
+ - - seed
53
+ - 2326823444
54
+ - - storage
55
+ - null
56
+ - - study_name
57
+ - null
58
+ - - tensorboard_log
59
+ - runs/BeamRiderNoFrameskip-v4__qrdqn__2326823444__1655916649
60
+ - - track
61
+ - true
62
+ - - trained_agent
63
+ - /content/drive/MyDrive/ML/qrdqn/BeamRiderNoFrameskip-v4_4/best_model.zip
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 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - env_wrapper
3
+ - - stable_baselines3.common.atari_wrappers.AtariWrapper
4
+ - - exploration_fraction
5
+ - 0.025
6
+ - - frame_stack
7
+ - 3
8
+ - - n_timesteps
9
+ - 10000000.0
10
+ - - optimize_memory_usage
11
+ - true
12
+ - - policy
13
+ - CnnPolicy
env_kwargs.yml ADDED
@@ -0,0 +1 @@
 
 
1
+ {}
qrdqn-BeamRiderNoFrameskip-v4.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:518eb2f8763e449db67a9ba143e12003bf0b8a8e3a87738d9bb64ff9196b0429
3
+ size 41866493
qrdqn-BeamRiderNoFrameskip-v4/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 1.5.1a8
qrdqn-BeamRiderNoFrameskip-v4/data ADDED
The diff for this file is too large to render. See raw diff
 
qrdqn-BeamRiderNoFrameskip-v4/policy.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02b7fac26af9e0698a81745578e62ba07e281a45eeb1a56e0a66873a8036f568
3
+ size 20849321
qrdqn-BeamRiderNoFrameskip-v4/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0760b4b1192c87b2b5417a5deefd49375c78aaed0f7dcfb6940de875e01e594c
3
+ size 20851561
qrdqn-BeamRiderNoFrameskip-v4/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-BeamRiderNoFrameskip-v4/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: 1.5.1a8
4
+ PyTorch: 1.11.0+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:e6d5b58fd81edf6785dfbdbd3fd9e0dc7f8f5a1a8189b0e23e42473483b80352
3
+ size 388689
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": 13335.0, "std_reward": 5701.878094101978, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-06-23T08:19:02.306273"}
train_eval_metrics.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:029583eef889cf451012e68fa14997c603c0290bc04d3efc8129942b4c6fec29
3
+ size 49098