Hugging Face's logo

Megalino111
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
Megalino111 commited on
Commit
f77e41c
·
1 Parent(s): 35e390f

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 +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: 94.50 +/- 71.18
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', 1e-05),
74
  ('learning_starts', 100000),
75
- ('n_timesteps', 500000.0),
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: 464.50 +/- 115.44
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', 1000000.0),
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
- - 411884796
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 2292003827
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -14,11 +14,11 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 1.0e-05
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 500000.0
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
+ - 1000000.0
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 sha256:7063b63deaa00867da0253a2ff0918ea835db4f37765ec270ae0f416ad5a5a83
3
- size 27220119
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b92dda556405058dccda1219fb407f62b89336767cae21a897cb14496825694
3
+ size 27220122
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:f2c6901cd07e0d5297ca8b450a8f341ef6bbf1caab721a4dd8884521f594d6c3
3
  size 13506236
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8292ec8f15a6ad8e8a593bd8fbcd87f3b0a7c5fe758d0c9a573eab14d07a0f9
3
  size 13506236
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:44eed15ad3f454e0716d202a24dcd20d38bf2fc077c1240a674dcabac5ec38ca
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:264e340a691317755d4fe14cf45ed22563d67651e9312d3569b85849ae7c510b
3
  size 13505370
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31aac6a5e4298db89a8bc33f1437ca3da84230c455066fcd850fe2f7c68577d3
3
- size 215456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2e5b7c215f545496bcd9e6bcc74ed12a6d24bf5a44202fd0502fec955898ab8
3
+ size 211240
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 94.5, "std_reward": 71.18461912520148, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-11-02T01:47:21.969192"}
 
1
+ {"mean_reward": 464.5, "std_reward": 115.44370922661832, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-11-04T02:32:19.581799"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:517f74850af047ac8337ca1c6e3d05773b653353f5de315c1d4b7dcc7087b23f
3
- size 21088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95c73be3d6a6c21189d03ef2469d23bec3733751f9253fe4aeb65320a9ea4734
3
+ size 36185