Hugging Face's logo

nivaldoho
/
dqn-SpaceInvaders

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
nivaldoho commited on
Commit
d7b8ac7
•
1 Parent(s): e440718

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 +2 -2
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +2 -2
  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: 473.50 +/- 175.00
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -63,12 +63,12 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
63
  ## Hyperparameters
64
  ```python
65
  OrderedDict([('batch_size', 64),
66
- ('buffer_size', 1000000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
70
  ('exploration_fraction', 0.025),
71
- ('frame_stack', 4),
72
  ('gamma', 0.99),
73
  ('gradient_steps', 1),
74
  ('learning_rate', 5e-05),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 316.00 +/- 141.29
20
  name: mean_reward
21
  verified: false
22
  ---
 
63
  ## Hyperparameters
64
  ```python
65
  OrderedDict([('batch_size', 64),
66
+ ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
70
  ('exploration_fraction', 0.025),
71
+ ('frame_stack', 2),
72
  ('gamma', 0.99),
73
  ('gradient_steps', 1),
74
  ('learning_rate', 5e-05),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 1953907537
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 1566579183
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -2,7 +2,7 @@
2
  - - - batch_size
3
  - 64
4
  - - buffer_size
5
- - 1000000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
@@ -10,7 +10,7 @@
10
  - - exploration_fraction
11
  - 0.025
12
  - - frame_stack
13
- - 4
14
  - - gamma
15
  - 0.99
16
  - - gradient_steps
 
2
  - - - batch_size
3
  - 64
4
  - - buffer_size
5
+ - 100000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
 
10
  - - exploration_fraction
11
  - 0.025
12
  - - frame_stack
13
+ - 2
14
  - - gamma
15
  - 0.99
16
  - - gradient_steps
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:74adc4d366c25b3f4c69113823e702153e52cad21bd864fd18795ecf42612836
3
- size 27220137
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4b27a30aab0bbd6ff67409046976fa48bf5114fee0e876d2d968380b6b3b636
3
+ size 27058634
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:d35e56949bb8082578b879f15c561ded04858a0af525215e3e1a85d93c341a2c
3
- size 13506236
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dc27f4ee0d278017756c730ca9534cbb3b0fc68b46499fcb98ab9bb7d650125
3
+ size 13473404
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:254031efd4c17717c1cf1d120aded031b44328ce03f8f94c0909f5624a2e1e02
3
- size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18ab39c557d5ac5bfee6709495af39ff923e4a4a833ded7d5c179c3311014a19
3
+ size 13472602
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15d9c20314dcd8f617fd0385ac4229634af9a897972918c6df60978b40c5d4ca
3
- size 191225
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:433fed1cc53a6594a86ad2973dbfd969641689d854084297154ca0cc2756a104
3
+ size 239906
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 473.5, "std_reward": 175.00071428425656, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-01-01T18:27:14.122267"}
 
1
+ {"mean_reward": 316.0, "std_reward": 141.2940196894405, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-01-01T19:39:50.737537"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99a891acf2bd163ba08593944e39ad9b4fdae0ce8ee5f082c741c5be98fc890b
3
- size 39178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89c93cfa2b72a76d4cccfa16cc6112fb843d5be177ac2a28b99e51227e2759d7
3
+ size 44351