Hugging Face's logo

Hrou
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
Hrou commited on
Commit
be59fe2
·
verified ·
1 Parent(s): 04365d8

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: 168.50 +/- 102.64
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),
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: 383.00 +/- 186.13
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),
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
- - 2130787734
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 3987531630
60
  - - storage
61
  - null
62
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 300000
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 600000
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 sha256:794c86fe1981bd6bbcad51a769763f2adcb353aafb38819a1ad89c89497d57a4
3
- size 27220508
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:545fdce5531cfa82692ee3ae7f1a590ba71ff922659748ac8d8b95078db8ed5c
3
+ size 27220509
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 sha256:4a6766cd3f5eb2fe9a0bd6aea365653a5c87dcae8dc53fdede91642c28ee156b
3
  size 13505852
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de7646d6941abeb9faf0a700ce05a96cfc20b9ac2f76fb490774a0c54a008872
3
  size 13505852
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7416ed4afae4d8ce906cf3f4529fc7d4557c3bf72562bc82f6f2d3130c740bd3
3
  size 13505178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3939bd2ae488953cd1b8519f67c2d53466c2e898d36f269c2a21183d5b80f36f
3
  size 13505178
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 168.5, "std_reward": 102.64136593011611, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-02-17T02:50:10.523943"}
 
1
+ {"mean_reward": 383.0, "std_reward": 186.13436007357697, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-02-17T21:23:37.275989"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b62eef21f67ed45f7a46f9e73be893a5a0738f98be558ef4abe5c0dc3ea5e311
3
- size 14150
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a5f098ef37263920edc1713dba36dd4d3b0e7e50e9cd07c81a9dd54dc0bfd09
3
+ size 25861