Hugging Face's logo

saintzeno
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files
xet
Community
saintzeno commited on
Commit
82c1c5c
·
1 Parent(s): ed794f1

Initial commit

Browse files
Files changed (11) hide show
  1. README.md +86 -86
  2. args.yml +81 -81
  3. config.yml +29 -29
  4. dqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
  5. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  6. dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +2 -2
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +2 -2
  8. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +5 -5
  9. env_kwargs.yml +1 -1
  10. results.json +1 -1
  11. train_eval_metrics.zip +2 -2
README.md CHANGED
@@ -1,86 +1,86 @@
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: 284.50 +/- 147.47
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 saintzeno -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 saintzeno -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 saintzeno
61
- ```
62
-
63
- ## Hyperparameters
64
- ```python
65
- OrderedDict([('batch_size', 48),
66
- ('buffer_size', 50000),
67
- ('env_wrapper',
68
- ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
- ('exploration_final_eps', 0.01),
70
- ('exploration_fraction', 0.1),
71
- ('frame_stack', 4),
72
- ('gradient_steps', 1),
73
- ('learning_rate', 0.001),
74
- ('learning_starts', 10000),
75
- ('n_timesteps', 1500000),
76
- ('optimize_memory_usage', False),
77
- ('policy', 'CnnPolicy'),
78
- ('target_update_interval', 1000),
79
- ('train_freq', 4),
80
- ('normalize', False)])
81
- ```
82
-
83
- # Environment Arguments
84
- ```python
85
- {'render_mode': 'rgb_array'}
86
- ```
 
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: 643.50 +/- 182.65
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 saintzeno -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 saintzeno -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 saintzeno
61
+ ```
62
+
63
+ ## Hyperparameters
64
+ ```python
65
+ OrderedDict([('batch_size', 48),
66
+ ('buffer_size', 100000),
67
+ ('env_wrapper',
68
+ ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
+ ('exploration_final_eps', 0.01),
70
+ ('exploration_fraction', 0.1),
71
+ ('frame_stack', 4),
72
+ ('gradient_steps', 1),
73
+ ('learning_rate', 0.0001),
74
+ ('learning_starts', 50000),
75
+ ('n_timesteps', 2000000),
76
+ ('optimize_memory_usage', False),
77
+ ('policy', 'CnnPolicy'),
78
+ ('target_update_interval', 1000),
79
+ ('train_freq', 4),
80
+ ('normalize', False)])
81
+ ```
82
+
83
+ # Environment Arguments
84
+ ```python
85
+ {'render_mode': 'rgb_array'}
86
+ ```
args.yml CHANGED
@@ -1,81 +1,81 @@
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
- - 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
- - 2388937159
58
- - - storage
59
- - null
60
- - - study_name
61
- - null
62
- - - tensorboard_log
63
- - ''
64
- - - track
65
- - false
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
- - null
78
- - - wandb_project_name
79
- - sb3
80
- - - wandb_tags
81
- - []
 
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
+ - 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
+ - 947261631
58
+ - - storage
59
+ - null
60
+ - - study_name
61
+ - null
62
+ - - tensorboard_log
63
+ - ''
64
+ - - track
65
+ - false
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
+ - null
78
+ - - wandb_project_name
79
+ - sb3
80
+ - - wandb_tags
81
+ - []
config.yml CHANGED
@@ -1,29 +1,29 @@
1
- !!python/object/apply:collections.OrderedDict
2
- - - - batch_size
3
- - 48
4
- - - buffer_size
5
- - 50000
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
- - 0.001
18
- - - learning_starts
19
- - 10000
20
- - - n_timesteps
21
- - 1500000
22
- - - optimize_memory_usage
23
- - false
24
- - - policy
25
- - CnnPolicy
26
- - - target_update_interval
27
- - 1000
28
- - - train_freq
29
- - 4
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - batch_size
3
+ - 48
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
+ - 50000
20
+ - - n_timesteps
21
+ - 2000000
22
+ - - optimize_memory_usage
23
+ - false
24
+ - - policy
25
+ - CnnPolicy
26
+ - - target_update_interval
27
+ - 1000
28
+ - - train_freq
29
+ - 4
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9fd8b9392ac838846ca7fa0034e55115b9e23e69e39650a341f93bd3d3d852c4
3
- size 27218385
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bc712fdb57a36aaf3699f10178841bbca79647db7324f91fc871e223d9ab659
3
+ size 27217774
dqn-SpaceInvadersNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41795c490d2da9d99682195897e47de26260c725f162413099610750d180a76a
3
- size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef5d62b4617f05ed52a2eba5f395bc5ad79ca76b34bd08dbc6ef7b50cb746009
3
+ size 13505419
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe473995c47b1e130fe7201afa7faad82527d3a2644b60b23721b42c5f70b17d
3
- size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72925c0905898acb7d71583edb5ab635721c870a95db52cc3996c5a2a1f90152
3
+ size 13504745
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -1,9 +1,9 @@
1
- - OS: Linux-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023
2
- - Python: 3.10.12
3
  - Stable-Baselines3: 2.0.0
4
- - PyTorch: 2.0.1+cu118
5
- - GPU Enabled: True
6
- - Numpy: 1.22.4
7
  - Cloudpickle: 2.2.1
8
  - Gymnasium: 0.28.1
9
  - OpenAI Gym: 0.26.2
 
1
+ - OS: Windows-10-10.0.22621-SP0 10.0.22621
2
+ - Python: 3.10.11
3
  - Stable-Baselines3: 2.0.0
4
+ - PyTorch: 2.0.1+cpu
5
+ - GPU Enabled: False
6
+ - Numpy: 1.25.0
7
  - Cloudpickle: 2.2.1
8
  - Gymnasium: 0.28.1
9
  - OpenAI Gym: 0.26.2
env_kwargs.yml CHANGED
@@ -1 +1 @@
1
- render_mode: rgb_array
 
1
+ render_mode: rgb_array
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 284.5, "std_reward": 147.46948836962852, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-07-07T03:38:13.246406"}
 
1
+ {"mean_reward": 643.5, "std_reward": 182.6478852875116, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-07-08T16:48:05.706010"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d134b31523d4ac40e4e085dbf3184e93b1e1deabd879ac822d6cdfec678ab055
3
- size 60566
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:252219b7f12cc103ab75fe337c071c7766f797eb0a5759f9f254283fc1ec33d0
3
+ size 62345