Hugging Face's logo

abarekatain
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
abarekatain commited on
Commit
279974f
•
1 Parent(s): 0690590

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +4 -4
  2. args.yml +1 -1
  3. config.yml +3 -3
  4. dqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
  5. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  6. dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +1 -1
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
  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: 224.50 +/- 102.65
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -67,12 +67,12 @@ OrderedDict([('batch_size', 64),
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', 0.0003),
74
  ('learning_starts', 100000),
75
- ('n_timesteps', 10000000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 700.00 +/- 151.82
20
  name: mean_reward
21
  verified: false
22
  ---
 
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
  ('gradient_steps', 1),
73
+ ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 30000000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 88068691
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 4166114841
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -8,17 +8,17 @@
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
- - 0.0003
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 10000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
8
  - - exploration_final_eps
9
  - 0.01
10
  - - exploration_fraction
11
+ - 0.025
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
+ - 30000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12b698abb2308fa54f0e94190a96a48de6c43e95e3fb6e8378d7429cc70b0043
3
- size 27225255
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4501578f54fbb4013558c795b12f209f6afa11d08945e9fff7edca502eb358d1
3
+ size 27225257
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 sha256:9ed076834ce5dc2838f191e44c45eab0ad5711f903c4abc39cfbeb982fe1e2e6
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1c431c5740c51172e32f465a5a167a3e17df261d54e10cfbfdf3c5e04368721
3
  size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b88cbbe54e6cd71e02e14020627589de5a19fb99e8f5d432968bd5cb03f84594
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f04f007e9db9d49064374f2f9b4b9a4fb8d7b0a09b23c9c3c29d926ed4ec1e1
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c4993dc7ce9c0730abc2f28f1a15bd92cc090da9270e1784cda53ea07116d34
3
- size 244219
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05f504e47b18376bb825ebb55aa198b72d13a2d3ca585a79272367470309c1f3
3
+ size 175826
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 224.5, "std_reward": 102.65110812845617, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-02-28T09:57:29.548533"}
 
1
+ {"mean_reward": 700.0, "std_reward": 151.82226450688975, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-03-02T09:21:08.843290"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef8c9e37a5794e003d89f598be35fe6bfb37ca0bc7d132c8bebd3fe28efe40b5
3
- size 364314
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df18d3258e6c97ba5eb30609ea76ddf8674d944abd6c6f716ea9ef5811d81e3a
3
+ size 864785