Hugging Face's logo

einkai
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
einkai commited on
Commit
9c09832
·
verified ·
1 Parent(s): ff09f72

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: 248.00 +/- 103.52
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', 300000.0),
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: 572.50 +/- 219.75
20
  name: mean_reward
21
  verified: false
22
  ---
 
73
  ('gradient_steps', 1),
74
  ('learning_rate', 0.0001),
75
  ('learning_starts', 100000),
76
+ ('n_timesteps', 600000.0),
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
- - 4207936522
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 4277783364
60
  - - storage
61
  - null
62
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 300000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 600000.0
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 sha256:90488567ad2dd7c68ccc59e5a8fd5cce076dfb11c4b98ea1fefa96229b497538
3
- size 27220635
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c80258510d180121c86867cdaad32209bbb824e65f22f863b1dae2bac7d2980c
3
+ size 27220636
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 sha256:1e3f93fd5dbd51582aeaf3b342907bb54875f275186d02c2b37a00c0a94c0833
3
  size 13506172
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3110c231c73dac4629f8a42997e42c377befe1e530d670859c02ce11636e1664
3
  size 13506172
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:023550f16fa15f7ceab85bee13254a617e04674419b6812c8161610a4e367a6a
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f305d31440438c6d0cacc84e43171af63605c87503ad569c79db656ffcb92985
3
  size 13505370
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 248.0, "std_reward": 103.51811435686027, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-01-03T13:16:47.441257"}
 
1
+ {"mean_reward": 572.5, "std_reward": 219.75270191740532, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-01-03T14:06:33.673521"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b55fca3f84e42d48ca9320b120e9b96dee545e4f93d74bd6963763b940808f45
3
- size 14152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f298ce5bb6f88222581821f398b3b051722b037e72b79353548047691ce9e2e
3
+ size 25110