Hugging Face's logo

NemesisAlm
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
NemesisAlm commited on
Commit
2334a8a
·
1 Parent(s): 64a5ad3

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 +1 -1
  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: 241.00 +/- 122.43
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -70,9 +70,9 @@ OrderedDict([('batch_size', 32),
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
- ('learning_rate', 0.0005),
74
  ('learning_starts', 100000),
75
- ('n_timesteps', 1000000),
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: 720.50 +/- 180.59
20
  name: mean_reward
21
  verified: false
22
  ---
 
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
+ ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 1200000),
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
- - 2558186645
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 3206611044
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -14,11 +14,11 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.0005
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 1000000
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 0.0001
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 1200000
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 sha256:82ea497a4b55abe8e4f668258b73fae9816c2496e3b93ee232803b5c446a6174
3
  size 27218384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4e737845df827140ce7adcf8204d17f935d061f21ad5e2ca18f9cbfe2a5b790
3
  size 27218384
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 sha256:0fc361428a7af5f86ee85220da88ebdcdc4ce2a971d57556cd13d2104bcb86f0
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a13e6b9658a94af977a6fd6293031d3ef373a34608a49c8f433467020066e30
3
  size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:396f903043fde3f390a7144c847fa9b14beb6d48da858342741d1053bbcf3164
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46ed667b3c2a4a7cad584c907428adf97fefd3aa46ce3e7a6ff457b42f2be463
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b96a9843dfe0369e1e2a295f9ea94bb78c8e4ca737151fd60153ce2e682a7171
3
- size 246702
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a63fe8b105c12efd95b262f027d3f12b4413bad675a5d8c8b66c2ce2ff328446
3
+ size 225035
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 241.0, "std_reward": 122.42957159118053, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-07-19T20:48:29.140077"}
 
1
+ {"mean_reward": 720.5, "std_reward": 180.5886209039761, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-07-20T20:33:47.402055"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:809a0bbe6b296c81496fe8fbab4e84e834a11707a895df6d6cd7008e44c94041
3
- size 36661
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9f7f85b7fc099e04a1d4873297958676f8388b136b7cbf1e963b71de5285a84
3
+ size 42106