Hugging Face's logo

yaohuacn
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
yaohuacn commited on
Commit
ab75e6f
•
1 Parent(s): 8169a4e

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: 287.50 +/- 54.19
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -62,7 +62,7 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
62
 
63
  ## Hyperparameters
64
  ```python
65
- OrderedDict([('batch_size', 512),
66
  ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
@@ -72,7 +72,7 @@ OrderedDict([('batch_size', 512),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
- ('n_timesteps', 10000000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 643.50 +/- 292.06
20
  name: mean_reward
21
  verified: false
22
  ---
 
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
  ('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),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 1446731594
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 2026624160
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -1,6 +1,6 @@
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
- - 512
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 10000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 32
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 1000000.0
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:e21d268e7fc02c7c15d02a140636b60d05839c488266d4cbfb690e77c1c0cf04
3
- size 27219579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:313f26f650d036de79f2a79237f1941413f91e381b5001212d0ed53428244c4d
3
+ size 27219560
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 sha256:73674d6832afcdc0c3ad07c3a865c041e96df966f0b1c4e70d57b3896fa8ddb0
3
  size 13506236
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d68087b8087ca81a5bd64096982e7c0fade8463113e2e74396b4a9e986d17dbd
3
  size 13506236
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a9f3423f9631086c33a00a63beef10238ed01e88cb246b55e8e6c086c7d6e6da
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8c0c16d498a3d8018016678906deebf0c86a98fdcdaad748547d9f833e754ec
3
  size 13505370
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cdbb912000f098be087573fa6597dd3bf3c3a5c6b90c380e55fafb3dc1860613
3
- size 255124
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ac8a70ac5bf8a86acaa5a64f84ae3dacffa7c337366f28c509a3e1bf031eecb
3
+ size 239052
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 287.5, "std_reward": 54.18717560456533, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-08-10T21:28:42.920981"}
 
1
+ {"mean_reward": 643.5, "std_reward": 292.06206532173945, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-08-11T00:22:22.303981"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0314b9209e9bedca5e95ee58f0edb1b80d7108d00ba0bc2783eb281105cfa8c9
3
- size 23092
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfe573df6cfe7d75d65d982b14efeea29ba8cbf4650748a5d2740f3f98aa7b37
3
+ size 35867