Hugging Face's logo

debisoft
/
SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
Community
debisoft commited on
Commit
2580542
·
verified ·
1 Parent(s): 8831d20

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +3 -3
  2. args.yml +1 -1
  3. config.yml +2 -2
  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: 257.00 +/- 38.81
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -63,7 +63,7 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
63
 
64
  ## Hyperparameters
65
  ```python
66
- OrderedDict([('batch_size', 32),
67
  ('buffer_size', 100000),
68
  ('env_wrapper',
69
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
@@ -71,7 +71,7 @@ OrderedDict([('batch_size', 32),
71
  ('exploration_fraction', 0.1),
72
  ('frame_stack', 4),
73
  ('gradient_steps', 1),
74
- ('learning_rate', 0.001),
75
  ('learning_starts', 100000),
76
  ('n_timesteps', 1000000.0),
77
  ('optimize_memory_usage', False),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 530.00 +/- 175.01
20
  name: mean_reward
21
  verified: false
22
  ---
 
63
 
64
  ## Hyperparameters
65
  ```python
66
+ OrderedDict([('batch_size', 64),
67
  ('buffer_size', 100000),
68
  ('env_wrapper',
69
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
 
71
  ('exploration_fraction', 0.1),
72
  ('frame_stack', 4),
73
  ('gradient_steps', 1),
74
+ ('learning_rate', 0.0001),
75
  ('learning_starts', 100000),
76
  ('n_timesteps', 1000000.0),
77
  ('optimize_memory_usage', False),
args.yml CHANGED
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 940535275
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 1640585640
60
  - - storage
61
  - null
62
  - - study_name
config.yml CHANGED
@@ -1,6 +1,6 @@
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
- - 32
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
@@ -14,7 +14,7 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.001
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 64
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 0.0001
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1b1dcfbc455f4902e743a4a1e03571eee05216d3ce440335b6b65617ea847fc
3
- size 27219627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da23455ecf413689ff31355fd9ac8ab63fc9aabee5a2334c55e3c9463cb097b8
3
+ size 27219629
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 sha256:88487bb4b0f0adbaa87f6411145589e734aeb1893b12ef2c70cbfad65b66a234
3
  size 13506569
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:928ce5643f493c92b5dc391435886120b3ba6a9d8a9702ecd1470dc15760ac7e
3
  size 13506569
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ac572c79e435bf8f18e227d50afc006f89e7e8ad2b9d870ecef887f98dba1cc
3
  size 13505767
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:179861087c03614aa91bece1ac1b2b4b2edd8c1408d5c31669ff422d01d2fc52
3
  size 13505767
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ea07c01915a2caa59cdb3e4728efe266b1af65268e459ecbbb534c14d29b3bc
3
- size 246606
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42d15ab68fb5653e265ac1148e060d82941f388fd70e070b25bded48161ea2e6
3
+ size 188248
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 257.0, "std_reward": 38.80721582386451, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-09-23T04:28:28.565545"}
 
1
+ {"mean_reward": 530.0, "std_reward": 175.01428513124293, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-09-23T05:19:50.767680"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd5eef239a4aceb190d1f245b0534f0abfe55010f742dee39e27aff33f6ed557
3
- size 40014
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daa3926e2e1cbcfa0e397f84d28ed43af021e0e5d65698e158adb2e4beb432c4
3
+ size 36768