Hugging Face's logo

nivaldoho
/
dqn-SpaceInvaders

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
nivaldoho commited on
Commit
41a005b
•
1 Parent(s): e391ff1

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +3 -3
  2. args.yml +1 -1
  3. config.yml +2 -2
  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. replay.mp4 +2 -2
  9. results.json +1 -1
  10. 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: 488.00 +/- 176.62
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -63,12 +63,12 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
63
  ## Hyperparameters
64
  ```python
65
  OrderedDict([('batch_size', 64),
66
- ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
70
  ('exploration_fraction', 0.025),
71
- ('frame_stack', 4),
72
  ('gamma', 0.99),
73
  ('gradient_steps', 1),
74
  ('learning_rate', 5e-05),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 535.50 +/- 110.37
20
  name: mean_reward
21
  verified: false
22
  ---
 
63
  ## Hyperparameters
64
  ```python
65
  OrderedDict([('batch_size', 64),
66
+ ('buffer_size', 700000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
70
  ('exploration_fraction', 0.025),
71
+ ('frame_stack', 2),
72
  ('gamma', 0.99),
73
  ('gradient_steps', 1),
74
  ('learning_rate', 5e-05),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 1675566432
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 248694835
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -2,7 +2,7 @@
2
  - - - batch_size
3
  - 64
4
  - - buffer_size
5
- - 100000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
@@ -10,7 +10,7 @@
10
  - - exploration_fraction
11
  - 0.025
12
  - - frame_stack
13
- - 4
14
  - - gamma
15
  - 0.99
16
  - - gradient_steps
 
2
  - - - batch_size
3
  - 64
4
  - - buffer_size
5
+ - 700000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
 
10
  - - exploration_fraction
11
  - 0.025
12
  - - frame_stack
13
+ - 2
14
  - - gamma
15
  - 0.99
16
  - - gradient_steps
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d9ad7baa1319b882ce73ec0fe974d6109ef04d8c8a23a387242242888763222
3
- size 27220134
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b01b048f8946f5dda185df956e39784c06ca5954cc063904ccee8ab6e9c081e7
3
+ size 27058634
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 sha256:58083e6d9f6381afd1cacd3f7130f2c81ffe685100bf88174f7dc73e5015444a
3
- size 13506236
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e94517e0d60d7e13484704cb0903f8cff746bc7001386e92a887f1c715f743aa
3
+ size 13473404
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19670fa9924ed8433310a795e48a7366f97210e249ec992a7076262394b34736
3
- size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f06f61a09db26a86d684b56c563bf07d013659a4bcea4ae3572c72bcad7cca5
3
+ size 13472602
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a344103ea306cb3883bfab7020ca7e6ca657ef09b6bc92bf0b3c5dab655c1da
3
- size 239090
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07941a6ce97a2ecd58c52f96bca5bd5b14f1a1bed8c9321ed62873bc48ed0f04
3
+ size 232994
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 488.0, "std_reward": 176.62389419328292, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-01-01T21:20:44.065291"}
 
1
+ {"mean_reward": 535.5, "std_reward": 110.3732304501413, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-01-01T22:50:27.847143"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f4def5c3d5f6af10af5d847b0fe8da8049d3820b6557cf540b2d0b0dfaf9c0c
3
- size 43497
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25eed5df63aab82486c90ae2af30979cd262ba75408c91ca78f3f2cf2607cea2
3
+ size 41891