Hugging Face's logo

carlosmirandad
/
rl-class-dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
carlosmirandad commited on
Commit
ccc3b71
•
1 Parent(s): 830fbb9

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +2 -2
  2. args.yml +1 -1
  3. config.yml +1 -1
  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: 154.00 +/- 100.72
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -72,7 +72,7 @@ OrderedDict([('batch_size', 32),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0005),
74
  ('learning_starts', 100000),
75
- ('n_timesteps', 12000000.0),
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: 531.50 +/- 134.70
20
  name: mean_reward
21
  verified: false
22
  ---
 
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0005),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 5000000.0),
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
- - 3073964619
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 244106226
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 12000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 5000000.0
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 sha256:32f6d91bacb6b9b5c3d5f81a3b518d57859f6ebb2b253334aed63626d1f380d0
3
- size 27224824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8a4184ef25daafb00f2af0faeed6e320e11198a8a4e86dbad8fe1c1fa36b90c
3
+ size 27224821
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:f966fde6f9c15350d1c58dcd6191f136911f326d9f0bf831cfbbade280d9abec
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0604e0871fd6bb860bca9c885ba828a8d33dcb13da8497e585e7f2a009d70d61
3
  size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75b87a1f5b473904e8b9120b9ec161d06b4ffce7240dd8f750a6ce6d69697e0d
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c3edbeb9066e4f600a6965733381cb19251bc61c1c8208fa0fe9dcbb819728b
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d2a4680600e94a7fdb11b5d1380bc1f6d2527e60f38b252ac7657ba69230731
3
- size 239232
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cf657285364965366e88fb7f180743726a18e84f3ea612139801760f4c8a1d5
3
+ size 214970
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 154.0, "std_reward": 100.71742649611338, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-25T23:56:49.655594"}
 
1
+ {"mean_reward": 531.5, "std_reward": 134.70430579606577, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-26T07:24:59.773767"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3f1eec24e76a28ae809e79c79e22b45e4ba63102055e70bd19979b98331bf4c
3
- size 405227
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ff691f369a585917389638052ea01613a14c76f9bd3810606425ba2521d0e5a
3
+ size 156549