Hugging Face's logo

haris9873
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
 Community
haris9873 commited on
Commit
df7b700
·
verified ·
1 Parent(s): fe4189c

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: 225.00 +/- 53.39
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', 200000),
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: 285.00 +/- 73.79
20
  name: mean_reward
21
  verified: false
22
  ---
 
73
  ('gradient_steps', 1),
74
  ('learning_rate', 0.0001),
75
  ('learning_starts', 100000),
76
+ ('n_timesteps', 400000),
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
- - 2345989778
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 930778782
60
  - - storage
61
  - null
62
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 200000
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 400000
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:cfb09bbf04d853fd494e2b283620671462e4e297df48628deee0caf73657b2b1
3
- size 27219608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b589c1ab330801adc754832fa294fced3a7af3e3e73c801f71d1a67c65234465
3
+ size 27219612
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:e6f577dbc33a4edad1038afd80b85863b74dc537b6d074e553eb84d3d26080d7
3
  size 13506569
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fe7fc0b30cc3008a5b3e1d2194e0cd6b9e6a0cdb6d9c37cc371e2ebc7926406
3
  size 13506569
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:987b562f413a1552e061266c8df6c42c3920195defa094753300fb3e60ddb6e9
3
  size 13505767
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85136c3ee1c3f7e7a79b94a610145a02b57ff98bba237ffd8a8acb3cc9fa573f
3
  size 13505767
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 225.0, "std_reward": 53.38539126015655, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-10-01T14:23:30.014341"}
 
1
+ {"mean_reward": 285.0, "std_reward": 73.79024325749306, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-10-01T14:49:06.963756"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7082f3e0c50bd93da53cebca3effa6af0819cfd7f9352c4719da712db6da3d57
3
- size 9609
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe47ff9b6812f1e84ff076788303d282cc1f24e140f8985dd0373aa59ea770f1
3
+ size 18212