egdethomas commited on
Commit
27639cb
1 Parent(s): ce256cd

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
+ - BeamRiderNoFrameskip-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: BeamRiderNoFrameskip-v4
16
+ type: BeamRiderNoFrameskip-v4
17
+ metrics:
18
+ - type: mean_reward
19
+ value: 52.80 +/- 38.36
20
+ name: mean_reward
21
+ verified: false
22
+ ---
23
+
24
+ # **DQN** Agent playing **BeamRiderNoFrameskip-v4**
25
+ This is a trained model of a **DQN** agent playing **BeamRiderNoFrameskip-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
+ SBX (SB3 + Jax): https://github.com/araffin/sbx
39
+
40
+ Install the RL Zoo (with SB3 and SB3-Contrib):
41
+ ```bash
42
+ pip install rl_zoo3
43
+ ```
44
+
45
+ ```
46
+ # Download model and save it into the logs/ folder
47
+ python -m rl_zoo3.load_from_hub --algo dqn --env BeamRiderNoFrameskip-v4 -orga egdethomas -f logs/
48
+ python -m rl_zoo3.enjoy --algo dqn --env BeamRiderNoFrameskip-v4 -f logs/
49
+ ```
50
+
51
+ If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
52
+ ```
53
+ python -m rl_zoo3.load_from_hub --algo dqn --env BeamRiderNoFrameskip-v4 -orga egdethomas -f logs/
54
+ python -m rl_zoo3.enjoy --algo dqn --env BeamRiderNoFrameskip-v4 -f logs/
55
+ ```
56
+
57
+ ## Training (with the RL Zoo)
58
+ ```
59
+ python -m rl_zoo3.train --algo dqn --env BeamRiderNoFrameskip-v4 -f logs/
60
+ # Upload the model and generate video (when possible)
61
+ python -m rl_zoo3.push_to_hub --algo dqn --env BeamRiderNoFrameskip-v4 -f logs/ -orga egdethomas
62
+ ```
63
+
64
+ ## Hyperparameters
65
+ ```python
66
+ OrderedDict([('batch_size', 32),
67
+ ('buffer_size', 100000),
68
+ ('env_wrapper',
69
+ ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
70
+ ('exploration_final_eps', 0.01),
71
+ ('exploration_fraction', 0.1),
72
+ ('frame_stack', 4),
73
+ ('gradient_steps', 1),
74
+ ('learning_rate', 0.0001),
75
+ ('learning_starts', 100000),
76
+ ('n_timesteps', 10000),
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 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - algo
3
+ - dqn
4
+ - - conf_file
5
+ - dqn.yml
6
+ - - device
7
+ - auto
8
+ - - env
9
+ - BeamRiderNoFrameskip-v4
10
+ - - env_kwargs
11
+ - null
12
+ - - eval_env_kwargs
13
+ - null
14
+ - - eval_episodes
15
+ - 5
16
+ - - eval_freq
17
+ - 25000
18
+ - - gym_packages
19
+ - []
20
+ - - hyperparams
21
+ - null
22
+ - - log_folder
23
+ - logs/
24
+ - - log_interval
25
+ - -1
26
+ - - max_total_trials
27
+ - null
28
+ - - n_eval_envs
29
+ - 1
30
+ - - n_evaluations
31
+ - null
32
+ - - n_jobs
33
+ - 1
34
+ - - n_startup_trials
35
+ - 10
36
+ - - n_timesteps
37
+ - -1
38
+ - - n_trials
39
+ - 500
40
+ - - no_optim_plots
41
+ - false
42
+ - - num_threads
43
+ - -1
44
+ - - optimization_log_path
45
+ - null
46
+ - - optimize_hyperparameters
47
+ - false
48
+ - - progress
49
+ - false
50
+ - - pruner
51
+ - median
52
+ - - sampler
53
+ - tpe
54
+ - - save_freq
55
+ - -1
56
+ - - save_replay_buffer
57
+ - false
58
+ - - seed
59
+ - 4194265549
60
+ - - storage
61
+ - null
62
+ - - study_name
63
+ - null
64
+ - - tensorboard_log
65
+ - ''
66
+ - - track
67
+ - false
68
+ - - trained_agent
69
+ - ''
70
+ - - truncate_last_trajectory
71
+ - true
72
+ - - uuid
73
+ - false
74
+ - - vec_env
75
+ - dummy
76
+ - - verbose
77
+ - 1
78
+ - - wandb_entity
79
+ - null
80
+ - - wandb_project_name
81
+ - sb3
82
+ - - wandb_tags
83
+ - []
config.yml ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ - 0.01
10
+ - - exploration_fraction
11
+ - 0.1
12
+ - - frame_stack
13
+ - 4
14
+ - - gradient_steps
15
+ - 1
16
+ - - learning_rate
17
+ - 0.0001
18
+ - - learning_starts
19
+ - 100000
20
+ - - n_timesteps
21
+ - 10000
22
+ - - optimize_memory_usage
23
+ - false
24
+ - - policy
25
+ - CnnPolicy
26
+ - - target_update_interval
27
+ - 1000
28
+ - - train_freq
29
+ - 4
dqn-BeamRiderNoFrameskip-v4.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da39dcf60d8298af1aa3b405124619c8d313a0560f0f4a5a3c8bea68436773f3
3
+ size 13724018
dqn-BeamRiderNoFrameskip-v4/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 2.4.0
dqn-BeamRiderNoFrameskip-v4/data ADDED
The diff for this file is too large to render. See raw diff
 
dqn-BeamRiderNoFrameskip-v4/policy.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:215ea7d8898faa9284464c7109532cf36390d330fccab8d77eeba20628a32876
3
+ size 1120
dqn-BeamRiderNoFrameskip-v4/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:018e9f1ed1a2f7bb778185a57fc1d7ecdc69384a9817f51bdbc913c9c5ae71c5
3
+ size 13517658
dqn-BeamRiderNoFrameskip-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-BeamRiderNoFrameskip-v4/system_info.txt ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ - OS: Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024
2
+ - Python: 3.10.12
3
+ - Stable-Baselines3: 2.4.0
4
+ - PyTorch: 2.5.1+cu121
5
+ - GPU Enabled: True
6
+ - Numpy: 1.26.4
7
+ - Cloudpickle: 3.1.0
8
+ - Gymnasium: 1.0.0
9
+ - OpenAI Gym: 0.25.2
env_kwargs.yml ADDED
@@ -0,0 +1 @@
 
 
1
+ render_mode: rgb_array
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": 52.8, "std_reward": 38.358310703157926, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-12-11T06:18:00.659428"}
train_eval_metrics.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ac4d304a9966f14a983c685b1f3aa31af63fcfe79a103c08947c03a545f33b2
3
+ size 351