Hugging Face's logo

PampX
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
PampX commited on
Commit
f7239ad
•
1 Parent(s): 201c9c8

Initial commit

Browse files
Files changed (9) 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. results.json +1 -1
  9. 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: 767.00 +/- 285.11
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -73,7 +73,7 @@ OrderedDict([('batch_size', 32),
73
  ('gradient_steps', 1),
74
  ('learning_rate', 0.0001),
75
  ('learning_starts', 100000),
76
- ('n_timesteps', 1000000.0),
77
  ('optimize_memory_usage', False),
78
  ('policy', 'CnnPolicy'),
79
  ('target_update_interval', 1000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 722.50 +/- 209.19
20
  name: mean_reward
21
  verified: false
22
  ---
 
73
  ('gradient_steps', 1),
74
  ('learning_rate', 0.0001),
75
  ('learning_starts', 100000),
76
+ ('n_timesteps', 10000000.0),
77
  ('optimize_memory_usage', False),
78
  ('policy', 'CnnPolicy'),
79
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 378192274
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 3089627794
60
  - - storage
61
  - null
62
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 1000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 10000000.0
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:ec6edc2be7848d29e6d76bd5a07e38260e77df81317829a15364f52845480a13
3
- size 27220639
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc22826af774986aef49d426eb9e9bc9a14d2dc304bf8adaaf1d1bcbfdd8555c
3
+ size 27220646
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 sha256:5331420ba405e3caee3f2fe1ba6826a7c2b6fc0d4317c614ef98620d03b61194
3
  size 13506172
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b0f8263912df3f9c57974b45480c4a49fc3521aed6f0d3c4e945cf52d71110e
3
  size 13506172
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73079496a70b5e4d16e066e802bdc55c3f58b288dd2a0a76586b570606ab29ce
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0369c37399363ebc2fee15c2b4d3836016f17d87cf8d96f357352aad9a6f23b2
3
  size 13505370
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 767.0, "std_reward": 285.10699745884875, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-12-10T12:13:32.310862"}
 
1
+ {"mean_reward": 722.5, "std_reward": 209.19189754863834, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-12-11T14:26:33.881493"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b86967cd5bf0bae68abdeedad6a3e1cff02fb0ff98086de852e7e6edf7fbde4
3
- size 37269
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:113246d3099eb1887d4659f4d20a33bc1a18822864dc1530882b1b77a8b44f88
3
+ size 50543