Hugging Face's logo

hanslab37
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
hanslab37 commited on
Commit
a5a86e0
•
1 Parent(s): ec8d13f

Initial commit

Browse files
Files changed (9) hide show
  1. README.md +2 -2
  2. args.yml +1 -1
  3. config.yml +1 -1
  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. results.json +1 -1
  9. 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: 571.50 +/- 74.97
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -63,7 +63,7 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
63
 
64
  ## Hyperparameters
65
  ```python
66
- OrderedDict([('batch_size', 64),
67
  ('buffer_size', 100000),
68
  ('env_wrapper',
69
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 598.00 +/- 160.95
20
  name: mean_reward
21
  verified: false
22
  ---
 
63
 
64
  ## Hyperparameters
65
  ```python
66
+ OrderedDict([('batch_size', 32),
67
  ('buffer_size', 100000),
68
  ('env_wrapper',
69
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
args.yml CHANGED
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 153168505
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 1393357558
60
  - - storage
61
  - null
62
  - - study_name
config.yml CHANGED
@@ -1,6 +1,6 @@
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
- - 64
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 32
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd9ccb7033423dc9be5fa8ecbd2672ba99261b78da4239e2432f8d983a7c7fea
3
  size 27220968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9603ab6ff08898bc2483631840783d9e0b08515479842702a54b5dad37bf5caf
3
  size 27220968
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 sha256:9af081f7006bcdfa4241866f904805c1c1e602d5f5ec08ea794b7e63db6c76ca
3
  size 13506172
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc37d8c1a7fbd291417f96e703d3f16dde85f2151f2e895d4025aee529476f6a
3
  size 13506172
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b78b44e739bc0b933e74ca86c01f54f07d164dbaf55b25318c36982330b8fcb8
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1633150053647d594284f5ea55ab174d34fcc689dcedc3b5fa2930ee11bd9349
3
  size 13505370
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 571.5, "std_reward": 74.96832664532403, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-10-28T17:26:21.477657"}
 
1
+ {"mean_reward": 598.0, "std_reward": 160.9534094078159, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-10-28T19:19:20.491532"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b63d6bfdfb3318a5bb90e2c13b2680c73fcb7714f8432687d1ceebd52409aa8
3
- size 35917
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b42c74d8569e7b25a8b729c04ca0454f4d18a4acd5baf67b5330226b37fa13e3
3
+ size 35853