Hugging Face's logo

victorivus
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
victorivus commited on
Commit
bc7e2ed
•
1 Parent(s): a509c57

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +3 -2
  2. args.yml +2 -2
  3. config.yml +3 -1
  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: 130.50 +/- 26.02
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -62,12 +62,13 @@ 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', 100000),
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),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 444.00 +/- 97.00
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']),
69
  ('exploration_final_eps', 0.01),
70
  ('exploration_fraction', 0.1),
71
+ ('exploration_initial_eps', 0.05),
72
  ('frame_stack', 4),
73
  ('gradient_steps', 1),
74
  ('learning_rate', 0.0001),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 2963453598
58
  - - storage
59
  - null
60
  - - study_name
@@ -64,7 +64,7 @@
64
  - - track
65
  - false
66
  - - trained_agent
67
- - logs/dqn/SpaceInvadersNoFrameskip-v4_4/SpaceInvadersNoFrameskip-v4.zip
68
  - - truncate_last_trajectory
69
  - true
70
  - - uuid
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 3474027386
58
  - - storage
59
  - null
60
  - - study_name
 
64
  - - track
65
  - false
66
  - - trained_agent
67
+ - logs/dqn/SpaceInvadersNoFrameskip-v4_1/SpaceInvadersNoFrameskip-v4.zip
68
  - - truncate_last_trajectory
69
  - true
70
  - - uuid
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
@@ -9,6 +9,8 @@
9
  - 0.01
10
  - - exploration_fraction
11
  - 0.1
 
 
12
  - - frame_stack
13
  - 4
14
  - - gradient_steps
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 64
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
 
9
  - 0.01
10
  - - exploration_fraction
11
  - 0.1
12
+ - - exploration_initial_eps
13
+ - 0.05
14
  - - frame_stack
15
  - 4
16
  - - gradient_steps
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:592e9b6b10d853d2e9937bf7da31861856bff284873d7a882a0480d18526b505
3
- size 27224297
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3777963ce224de61eabe2307656a5a4f4c307041d073f51fdbd258d5b8fd8e6
3
+ size 27224299
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 sha256:15628554125f403e5cc75716bed9920e3e32c0e3e81e1c24a8368748be174a1d
3
  size 13505419
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb4db3243ad24342c84bd765fb2f0657441afdffa70021a09e70fb108f943090
3
  size 13505419
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27481d18fac8d0684d71992a5a342a8f0b5c025663ce62afbe108eabfc8aca6c
3
  size 13504745
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0fd88323c26ac10a962e93cacd5d9f29fcbca69d5bd92084cb781c535aa5be2
3
  size 13504745
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c1f37d2d7794daa13ebafda1edc0a3efb0b45cbb11e2ccabfb272befad4454b
3
- size 243969
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4aca082c099cfa6093b5b1aba64f2143502902f0cbb42fd14aa25948970ad90
3
+ size 236970
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 130.5, "std_reward": 26.02402735934621, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-02-15T16:57:02.536906"}
 
1
+ {"mean_reward": 444.0, "std_reward": 97.0, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-02-16T10:22:05.281451"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09b10703e7ab9b82b0e006f8a89819bab3ad42e579e7c88036f58df5846c7c6d
3
- size 7381
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40b04386d39858f9bd0395a41730f68bce6510b7cb3bfca75372c1146d266de1
3
+ size 12146