Hugging Face's logo

SpartanLondoner
/
dqn-MsPacmanNoFrameskip-v4

Reinforcement Learning
stable-baselines3
MsPacmanNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
SpartanLondoner commited on
Commit
322cbe2
•
1 Parent(s): 58dbade

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-MsPacmanNoFrameskip-v4.zip +1 -1
  5. dqn-MsPacmanNoFrameskip-v4/data +0 -0
  6. dqn-MsPacmanNoFrameskip-v4/policy.optimizer.pth +1 -1
  7. dqn-MsPacmanNoFrameskip-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: MsPacmanNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
- value: 2043.00 +/- 1029.09
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -62,7 +62,7 @@ python -m rl_zoo3.push_to_hub --algo dqn --env MsPacmanNoFrameskip-v4 -f logs/ -
62
 
63
  ## Hyperparameters
64
  ```python
65
- OrderedDict([('batch_size', 32),
66
  ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
@@ -72,7 +72,7 @@ OrderedDict([('batch_size', 32),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
- ('n_timesteps', 1000000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
 
16
  type: MsPacmanNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 1816.00 +/- 301.64
20
  name: mean_reward
21
  verified: false
22
  ---
 
62
 
63
  ## Hyperparameters
64
  ```python
65
+ OrderedDict([('batch_size', 64),
66
  ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
 
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 2000000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 1077733471
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 4016104834
58
  - - storage
59
  - null
60
  - - 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
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 1000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 64
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 2000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
dqn-MsPacmanNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:721c5b5804d6755c193b0683a25f477aefdc9546de048ddcfd0ff01b506e2c80
3
  size 27244694
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdb32c7be7fe1689cac2b946471f25455ecbddc7c24d68e2a7a4b16e364971cb
3
  size 27244694
dqn-MsPacmanNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
dqn-MsPacmanNoFrameskip-v4/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd6ef282ed40f4f160c62a80d0a8ab451bed85a0f58c276f728090e834e1c657
3
  size 13518524
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf7f927126ceef9e78e7086f11e69f2dee1aa4ec3931ced8eb67db4a755ef662
3
  size 13518524
dqn-MsPacmanNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92820804e6dc1925e645cbbeedd9b025d08ffe1ce7d692a48f90970fcc4413af
3
  size 13517658
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:220ef7b81217abaa7b3ae10143fec540864e0d84ff56e0e82bf49a02879ffd2f
3
  size 13517658
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69448889872c572a2b76a0e4897d9bcf214de1e11e64d5626da2a144f1cc7e9e
3
- size 242079
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8e04077556de7962ff2c9091315d1e0bbd177e02c85eca838277d9e8ea3d0e7
3
+ size 249665
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 2043.0, "std_reward": 1029.0874598400273, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-11-21T22:04:30.844859"}
 
1
+ {"mean_reward": 1816.0, "std_reward": 301.6355416723964, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-11-23T12:11:23.971229"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a457c1f6464572c3fb6532227a56d3c4f1a05c202aad18c863aedb0b7611607
3
- size 42268
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80da0c7e420545285ea0f138f04fb55fc9dc65e2fffa7ed8aa95cce320c98a9f
3
+ size 72334