Hugging Face's logo

SolomonBlue
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
SolomonBlue commited on
Commit
f63659a
·
verified ·
1 Parent(s): fd7c781

Initial commit

Browse files
Files changed (9) hide show
  1. README.md +5 -5
  2. args.yml +2 -2
  3. config.yml +4 -4
  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 +1 -1
  8. results.json +1 -1
  9. train_eval_metrics.zip +2 -2
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
- value: 160.00 +/- 155.69
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -63,16 +63,16 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
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', 1000000.0),
77
  ('optimize_memory_usage', False),
78
  ('policy', 'CnnPolicy'),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 195.00 +/- 73.18
20
  name: mean_reward
21
  verified: false
22
  ---
 
63
 
64
  ## Hyperparameters
65
  ```python
66
+ OrderedDict([('batch_size', 64),
67
+ ('buffer_size', 500000),
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', 0.00025),
75
+ ('learning_starts', 50000),
76
  ('n_timesteps', 1000000.0),
77
  ('optimize_memory_usage', False),
78
  ('policy', 'CnnPolicy'),
args.yml CHANGED
@@ -20,7 +20,7 @@
20
  - - hyperparams
21
  - null
22
  - - log_folder
23
- - logs/
24
  - - log_interval
25
  - -1
26
  - - max_total_trials
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 913935887
60
  - - storage
61
  - null
62
  - - study_name
 
20
  - - hyperparams
21
  - null
22
  - - log_folder
23
+ - logs
24
  - - log_interval
25
  - -1
26
  - - max_total_trials
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 743556992
60
  - - storage
61
  - null
62
  - - study_name
config.yml CHANGED
@@ -1,8 +1,8 @@
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
@@ -14,9 +14,9 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.0001
18
  - - learning_starts
19
- - 100000
20
  - - n_timesteps
21
  - 1000000.0
22
  - - optimize_memory_usage
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 64
4
  - - buffer_size
5
+ - 500000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 0.00025
18
  - - learning_starts
19
+ - 50000
20
  - - n_timesteps
21
  - 1000000.0
22
  - - optimize_memory_usage
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5fc9bd46a2209791062adc948efae296d6240e54057112929c793f3040696b8
3
- size 13712122
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed35bc7a7cab91d4071ad04edae1fcef56b3b9b2ee7fc2583a782e22a84ca1f6
3
+ size 27221023
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 sha256:215ea7d8898faa9284464c7109532cf36390d330fccab8d77eeba20628a32876
3
- size 1120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:815ef3bc8fddb110231d1189b38a9809ac7497b2269c660e34b4dea7c5722913
3
+ size 13506172
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c0019842e97b7124f224fea7cbcd97c71c8f3a8431655516feaa7cb4302ca27
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a49639c1937e17284bee37e6e9460988f5f2a62f576193305f5b26264bbf66c
3
  size 13505370
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 160.0, "std_reward": 155.6920036482285, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-01-18T13:46:39.448399"}
 
1
+ {"mean_reward": 195.0, "std_reward": 73.1778655059028, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-01-18T20:46:49.777933"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9a95832da2e49328c92b562c36f2edbaca64c92029a36fb2efe619c7dabcbd1
3
- size 349
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a52e9d799f78cf0a29b2f6d0a9dfb9bc5006b8d61e3a1dc3cbb1341fdc4ccca
3
+ size 9518