monti-python commited on
Commit
116097b
·
1 Parent(s): 87b43c4

Initial commit

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ *.mp4 filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: stable-baselines3
3
+ tags:
4
+ - SpaceInvadersNoFrameskip-v4
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: SpaceInvadersNoFrameskip-v4
16
+ type: SpaceInvadersNoFrameskip-v4
17
+ metrics:
18
+ - type: mean_reward
19
+ value: 539.50 +/- 133.72
20
+ name: mean_reward
21
+ verified: false
22
+ ---
23
+
24
+ # **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
25
+ This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4**
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 SpaceInvadersNoFrameskip-v4 -orga monti-python -f logs/
47
+ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -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 SpaceInvadersNoFrameskip-v4 -orga monti-python -f logs/
53
+ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
54
+ ```
55
+
56
+ ## Training (with the RL Zoo)
57
+ ```
58
+ python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
59
+ # Upload the model and generate video (when possible)
60
+ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga monti-python
61
+ ```
62
+
63
+ ## Hyperparameters
64
+ ```python
65
+ OrderedDict([('batch_size', 32),
66
+ ('buffer_size', 100000),
67
+ ('env_wrapper',
68
+ ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
+ ('exploration_final_eps', 0.001),
70
+ ('exploration_fraction', 0.1),
71
+ ('exploration_initial_eps', 0.01),
72
+ ('frame_stack', 4),
73
+ ('gradient_steps', 1),
74
+ ('learning_rate', 0.0001),
75
+ ('learning_starts', 100000),
76
+ ('n_timesteps', 1000000.0),
77
+ ('optimize_memory_usage', False),
78
+ ('policy', 'CnnPolicy'),
79
+ ('target_update_interval', 1000),
80
+ ('train_freq', 4),
81
+ ('normalize', False)])
82
+ ```
83
+
84
+ # Environment Arguments
85
+ ```python
86
+ {'render_mode': 'rgb_array'}
87
+ ```
args.yml ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - algo
3
+ - dqn
4
+ - - conf_file
5
+ - dqn.yml
6
+ - - device
7
+ - auto
8
+ - - env
9
+ - SpaceInvadersNoFrameskip-v4
10
+ - - env_kwargs
11
+ - null
12
+ - - eval_episodes
13
+ - 5
14
+ - - eval_freq
15
+ - 25000
16
+ - - gym_packages
17
+ - []
18
+ - - hyperparams
19
+ - exploration_final_eps: 0.001
20
+ exploration_initial_eps: 0.01
21
+ - - log_folder
22
+ - logs
23
+ - - log_interval
24
+ - -1
25
+ - - max_total_trials
26
+ - null
27
+ - - n_eval_envs
28
+ - 1
29
+ - - n_evaluations
30
+ - null
31
+ - - n_jobs
32
+ - 1
33
+ - - n_startup_trials
34
+ - 10
35
+ - - n_timesteps
36
+ - -1
37
+ - - n_trials
38
+ - 500
39
+ - - no_optim_plots
40
+ - false
41
+ - - num_threads
42
+ - -1
43
+ - - optimization_log_path
44
+ - null
45
+ - - optimize_hyperparameters
46
+ - false
47
+ - - progress
48
+ - false
49
+ - - pruner
50
+ - median
51
+ - - sampler
52
+ - tpe
53
+ - - save_freq
54
+ - -1
55
+ - - save_replay_buffer
56
+ - false
57
+ - - seed
58
+ - 3222641777
59
+ - - storage
60
+ - null
61
+ - - study_name
62
+ - null
63
+ - - tensorboard_log
64
+ - ''
65
+ - - track
66
+ - false
67
+ - - trained_agent
68
+ - logs/dqn/SpaceInvadersNoFrameskip-v4_5/SpaceInvadersNoFrameskip-v4.zip
69
+ - - truncate_last_trajectory
70
+ - true
71
+ - - uuid
72
+ - false
73
+ - - vec_env
74
+ - dummy
75
+ - - verbose
76
+ - 1
77
+ - - wandb_entity
78
+ - null
79
+ - - wandb_project_name
80
+ - sb3
81
+ - - wandb_tags
82
+ - []
config.yml ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - batch_size
3
+ - 32
4
+ - - buffer_size
5
+ - 100000
6
+ - - env_wrapper
7
+ - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
+ - - exploration_final_eps
9
+ - 0.001
10
+ - - exploration_fraction
11
+ - 0.1
12
+ - - exploration_initial_eps
13
+ - 0.01
14
+ - - frame_stack
15
+ - 4
16
+ - - gradient_steps
17
+ - 1
18
+ - - learning_rate
19
+ - 0.0001
20
+ - - learning_starts
21
+ - 100000
22
+ - - n_timesteps
23
+ - 1000000.0
24
+ - - optimize_memory_usage
25
+ - false
26
+ - - policy
27
+ - CnnPolicy
28
+ - - target_update_interval
29
+ - 1000
30
+ - - train_freq
31
+ - 4
dqn-SpaceInvadersNoFrameskip-v4.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ef4c32f57cd1cc922fff76ccb24be72e42e30a25df12bcfd3e482b1a5b8ff23
3
+ size 27220978
dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 2.3.2
dqn-SpaceInvadersNoFrameskip-v4/data ADDED
The diff for this file is too large to render. See raw diff
 
dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27d6ce60f11f116e8b2977568a4e058a76e5476c70eeccb45cd15a80f5c38aef
3
+ size 13506236
dqn-SpaceInvadersNoFrameskip-v4/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:119a5731942db12bc00d1fffb6098ae8fbc06734d3db38a3db7d111b08a35827
3
+ size 13505370
dqn-SpaceInvadersNoFrameskip-v4/pytorch_variables.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
3
+ size 864
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ - OS: Linux-5.15.153.1-microsoft-standard-WSL2-x86_64-with-glibc2.35 # 1 SMP Fri Mar 29 23:14:13 UTC 2024
2
+ - Python: 3.10.14
3
+ - Stable-Baselines3: 2.3.2
4
+ - PyTorch: 2.3.0+cu121
5
+ - GPU Enabled: True
6
+ - Numpy: 1.26.4
7
+ - Cloudpickle: 3.0.0
8
+ - Gymnasium: 0.28.1
9
+ - OpenAI Gym: 0.26.2
env_kwargs.yml ADDED
@@ -0,0 +1 @@
 
 
1
+ render_mode: rgb_array
replay.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdd5132a3d85491c71b787af55afe25f94a0858db6cf525f1f183cee0b6029ef
3
+ size 270215
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": 539.5, "std_reward": 133.72453028520982, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-06-16T14:05:24.669015"}
train_eval_metrics.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03ab494535b63cddba312bcb38a4cbddeb6bd22b9ed2965ef27b9aa78b93d3b5
3
+ size 29104