Hugging Face's logo

jliu596
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
jliu596 commited on
Commit
9bca636
·
1 Parent(s): 0c7fc44

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +5 -5
  2. args.yml +1 -1
  3. config.yml +4 -4
  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: 214.50 +/- 46.98
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -62,15 +62,15 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
62
 
63
  ## Hyperparameters
64
  ```python
65
- OrderedDict([('batch_size', 32),
66
  ('buffer_size', 1000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
- ('exploration_final_eps', 0.01),
70
- ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
- ('learning_rate', 0.0001),
74
  ('learning_starts', 1000),
75
  ('n_timesteps', 300000.0),
76
  ('optimize_memory_usage', False),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 142.50 +/- 11.88
20
  name: mean_reward
21
  verified: false
22
  ---
 
62
 
63
  ## Hyperparameters
64
  ```python
65
+ OrderedDict([('batch_size', 52),
66
  ('buffer_size', 1000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
+ ('exploration_final_eps', 0.001),
70
+ ('exploration_fraction', 1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
+ ('learning_rate', 0.001),
74
  ('learning_starts', 1000),
75
  ('n_timesteps', 300000.0),
76
  ('optimize_memory_usage', False),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 2437509047
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 4246315905
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -1,20 +1,20 @@
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
- - 32
4
  - - buffer_size
5
  - 1000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
9
- - 0.01
10
  - - exploration_fraction
11
- - 0.1
12
  - - frame_stack
13
  - 4
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.0001
18
  - - learning_starts
19
  - 1000
20
  - - n_timesteps
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 52
4
  - - buffer_size
5
  - 1000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
9
+ - 0.001
10
  - - exploration_fraction
11
+ - 1
12
  - - frame_stack
13
  - 4
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 0.001
18
  - - learning_starts
19
  - 1000
20
  - - n_timesteps
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89bf312f2b745aa332064391a1f7a36bb4a55b08a8e72f5e7a3645615b607bf7
3
- size 27218379
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84fb882052dabe3f9b1477c5eb5a83f2aac6f604ea08b762c7c9a7a0f1f07e5e
3
+ size 27218383
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 sha256:3aac3e6eb02260c4b19b81979c1bc03b8d18eb817cbf7df16b8f8af580f8489a
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cfe8240dddea83a3cde9e793f707ca6d05aad841e9abab7cdec6f6c87dd4aa0
3
  size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a0795caf7089c8f10f07b6246888e89662fac0d07c277167b9db8c221a0f571
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5480ab9902ae5ba7aeec9f576135b34119cc19fee9dbcf8ffbea9fbccd81d44e
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:04ca574b28b1dc949cef615815b90fdc32c191696f393cffe737aa96339a69aa
3
- size 271781
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76ce42c63b4f5d11efcf828d9af31f6cc73a69984036fc32a8b0b2b979e09473
3
+ size 255310
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 214.5, "std_reward": 46.98137929009748, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-07-07T16:01:52.864936"}
 
1
+ {"mean_reward": 142.5, "std_reward": 11.884864324004713, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-07-11T19:28:03.893121"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:069d47c7ca6d40cbbe2ecbe33774b06f1693426762df003176518e6770438a4a
3
- size 13144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42c8874c99af8bfcf49dcf4cc0f931f7b48915c0b9813762bfcc1e70716723bd
3
+ size 14579