Hugging Face's logo

renee127
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
renee127 commited on
Commit
b44e7c3
·
1 Parent(s): 10d2fd4

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 +1 -1
  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: 202.00 +/- 166.66
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -57,7 +57,7 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
57
 
58
  ## Hyperparameters
59
  ```python
60
- OrderedDict([('batch_size', 16),
61
  ('buffer_size', 100000),
62
  ('env_wrapper',
63
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
@@ -65,7 +65,7 @@ OrderedDict([('batch_size', 16),
65
  ('exploration_fraction', 0.1),
66
  ('frame_stack', 4),
67
  ('gradient_steps', 1),
68
- ('learning_rate', 1e-05),
69
  ('learning_starts', 100000),
70
  ('n_timesteps', 1000000.0),
71
  ('optimize_memory_usage', False),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 599.50 +/- 152.72
20
  name: mean_reward
21
  verified: false
22
  ---
 
57
 
58
  ## Hyperparameters
59
  ```python
60
+ OrderedDict([('batch_size', 32),
61
  ('buffer_size', 100000),
62
  ('env_wrapper',
63
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
 
65
  ('exploration_fraction', 0.1),
66
  ('frame_stack', 4),
67
  ('gradient_steps', 1),
68
+ ('learning_rate', 0.0001),
69
  ('learning_starts', 100000),
70
  ('n_timesteps', 1000000.0),
71
  ('optimize_memory_usage', False),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 3190759609
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 3075784790
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -1,6 +1,6 @@
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
- - 16
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
@@ -14,7 +14,7 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 1.0e-05
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 32
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 sha256:11f8df309f9bff907d3633c9142a54890a2170b783c23f28710f8f7e78a0e4c8
3
  size 27224794
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:206931725345fe758ad1b99b801512a93e3bf27f4c7d32045a83a6cf9ab99c54
3
  size 27224794
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 sha256:0101320e01c6327e975f69c985ebbbd41f2fd8e5a01ac0b21b9505d505d5f00c
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b01a9c84427d33a77c1e86e8e8671fff5ad00de3e84fcd8564f639087063f622
3
  size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c154afc19cb07094bb671fe85fccd41ff00f56c7af0ef1ed939e8fb980a2e50b
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:680b8ca971ac3d2f6b68e927cc433600fcd18acab4d601966813e337016a4b72
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ccce085ab34bb74e5204b706e1e224501fa12f8728ce97eaaa46f752fa0d81f0
3
- size 247586
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:802008da203d8d0549d246bfda9db076ba74c5fe2e963cab584d54284f773cbb
3
+ size 197522
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 202.0, "std_reward": 166.66133324799728, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-24T15:24:57.288856"}
 
1
+ {"mean_reward": 599.5, "std_reward": 152.71624013182094, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-24T17:43:58.464127"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b29dc28b0a5190e1062a38d59f7cd3978a17811d317f46e38cce35add9670566
3
- size 41915
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da4d8190ffe82efc01aa2cc58fae102a973ad0d0134bdf71448c8ca70c34bd42
3
+ size 36035