Hugging Face's logo

Corianas
/
dqn-BeamRiderNoFrameskip-v4

Reinforcement Learning
stable-baselines3
BeamRiderNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
 Community
Corianas commited on
Commit
271f040
·
1 Parent(s): 304caa2

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +3 -3
  2. args.yml +2 -2
  3. config.yml +2 -2
  4. dqn-BeamRiderNoFrameskip-v4.zip +2 -2
  5. dqn-BeamRiderNoFrameskip-v4/data +0 -0
  6. dqn-BeamRiderNoFrameskip-v4/policy.optimizer.pth +1 -1
  7. dqn-BeamRiderNoFrameskip-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
@@ -10,7 +10,7 @@ model-index:
10
  results:
11
  - metrics:
12
  - type: mean_reward
13
- value: 591.20 +/- 146.89
14
  name: mean_reward
15
  task:
16
  type: reinforcement-learning
@@ -59,8 +59,8 @@ OrderedDict([('batch_size', 32),
59
  ('frame_stack', 4),
60
  ('gradient_steps', 1),
61
  ('learning_rate', 0.0001),
62
- ('learning_starts', 10000),
63
- ('n_timesteps', 100000.0),
64
  ('optimize_memory_usage', True),
65
  ('policy', 'CnnPolicy'),
66
  ('target_update_interval', 1000),
 
10
  results:
11
  - metrics:
12
  - type: mean_reward
13
+ value: 3983.00 +/- 1512.41
14
  name: mean_reward
15
  task:
16
  type: reinforcement-learning
 
59
  ('frame_stack', 4),
60
  ('gradient_steps', 1),
61
  ('learning_rate', 0.0001),
62
+ ('learning_starts', 100000),
63
+ ('n_timesteps', 10000000.0),
64
  ('optimize_memory_usage', True),
65
  ('policy', 'CnnPolicy'),
66
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -50,7 +50,7 @@
50
  - - save_replay_buffer
51
  - false
52
  - - seed
53
- - 3602355214
54
  - - storage
55
  - null
56
  - - study_name
@@ -60,7 +60,7 @@
60
  - - track
61
  - false
62
  - - trained_agent
63
- - ''
64
  - - truncate_last_trajectory
65
  - true
66
  - - uuid
 
50
  - - save_replay_buffer
51
  - false
52
  - - seed
53
+ - 3153371912
54
  - - storage
55
  - null
56
  - - study_name
 
60
  - - track
61
  - false
62
  - - trained_agent
63
+ - /content/rl-baselines3-zoo/logs/dqn/BeamRiderNoFrameskip-v4_3/BeamRiderNoFrameskip-v4.zip
64
  - - truncate_last_trajectory
65
  - true
66
  - - uuid
config.yml CHANGED
@@ -16,9 +16,9 @@
16
  - - learning_rate
17
  - 0.0001
18
  - - learning_starts
19
- - 10000
20
  - - n_timesteps
21
- - 100000.0
22
  - - optimize_memory_usage
23
  - true
24
  - - policy
 
16
  - - learning_rate
17
  - 0.0001
18
  - - learning_starts
19
+ - 100000
20
  - - n_timesteps
21
+ - 10000000.0
22
  - - optimize_memory_usage
23
  - true
24
  - - policy
dqn-BeamRiderNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:acbdf0b4d0874b2e69279c999618496fa697e03e10b17052b613fdf9b4f4d85a
3
- size 27245532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96e3d2be5a146cd940aee59d6a1fc29fc4616540fd0c5b1211a3dac9900a4dc0
3
+ size 27246786
dqn-BeamRiderNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
dqn-BeamRiderNoFrameskip-v4/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba21cd8f50ee043d53c73cf5ec59f1212e69e4c7297aafffe8660292fbb92de2
3
  size 13515433
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ac3edbd6594fd737f5c9c92039dec7ae27ad1351133a4195d3c2915f7bfca7c
3
  size 13515433
dqn-BeamRiderNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:afd233521fe20b42ade5a78a375830cd57e87f3ccdfc89b28f667b4cf11425f8
3
  size 13517225
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3850ae8f551b596326575ab4a77f888044413da1e0eff5d43d33b3eeabf6d6f4
3
  size 13517225
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2db2b0ffecdf9344866591a4303f8d1712fa1e3ed3cff3e2ff3691d0d04be6b8
3
- size 344642
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91ce5028c13efe1a3d211493d02eb1fe27f2204bec7311da79ce7b39e03d8892
3
+ size 352663
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 591.2, "std_reward": 146.89097998175382, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-06-15T08:56:48.755327"}
 
1
+ {"mean_reward": 3983.0, "std_reward": 1512.4079476120191, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-06-15T10:41:40.225549"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af5d6c87d213bdb1505b72b15e0d5f88a5e8de47bb91667524f8b074ac8ee389
3
- size 3007
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8587fd68950d061f6719faae04f75504c1b1218bd604beb89476edfc3716621
3
+ size 15847