Hugging Face's logo

PabloTa
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
 Community
PabloTa commited on
Commit
83e35f4
·
1 Parent(s): 80afd70

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +8 -5
  2. args.yml +1 -1
  3. config.yml +10 -4
  4. qrdqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
  5. qrdqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  6. qrdqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +2 -2
  7. qrdqn-SpaceInvadersNoFrameskip-v4/policy.pth +2 -2
  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: 374.00 +/- 214.61
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -57,11 +57,14 @@ python -m rl_zoo3.push_to_hub --algo qrdqn --env SpaceInvadersNoFrameskip-v4 -f
57
 
58
  ## Hyperparameters
59
  ```python
60
- OrderedDict([('env_wrapper',
 
 
61
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
62
- ('exploration_fraction', 0.025),
63
- ('frame_stack', 4),
64
- ('n_timesteps', 10000000.0),
 
65
  ('normalize', False),
66
  ('optimize_memory_usage', False),
67
  ('policy', 'CnnPolicy')])
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 374.00 +/- 214.89
20
  name: mean_reward
21
  verified: false
22
  ---
 
57
 
58
  ## Hyperparameters
59
  ```python
60
+ OrderedDict([('batch_size', 128),
61
+ ('buffer_size', 25000),
62
+ ('env_wrapper',
63
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
64
+ ('exploration_fraction', 0.225),
65
+ ('frame_stack', 3),
66
+ ('learning_rate', 0.023),
67
+ ('n_timesteps', 1000000.0),
68
  ('normalize', False),
69
  ('optimize_memory_usage', False),
70
  ('policy', 'CnnPolicy')])
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 2716145110
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 239030764
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -1,12 +1,18 @@
1
  !!python/object/apply:collections.OrderedDict
2
- - - - env_wrapper
 
 
 
 
3
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
4
  - - exploration_fraction
5
- - 0.025
6
  - - frame_stack
7
- - 4
 
 
8
  - - n_timesteps
9
- - 10000000.0
10
  - - normalize
11
  - false
12
  - - optimize_memory_usage
 
1
  !!python/object/apply:collections.OrderedDict
2
+ - - - batch_size
3
+ - 128
4
+ - - buffer_size
5
+ - 25000
6
+ - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_fraction
9
+ - 0.225
10
  - - frame_stack
11
+ - 3
12
+ - - learning_rate
13
+ - 0.023
14
  - - n_timesteps
15
+ - 1000000.0
16
  - - normalize
17
  - false
18
  - - optimize_memory_usage
qrdqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fff5b1396cc4a901958c7db4e72e57d1115696aae4916bc139a8a198554e6551
3
- size 37024704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:120ef15d0209483649ecebe0e24b3ff58bf3cf66a97c61bf21c21e395521f859
3
+ size 36945029
qrdqn-SpaceInvadersNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
qrdqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c441c8f52d4af97870e05a40abdcdf9499e9e45023f5c239298fda57c1903ca
3
- size 18405643
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9244e5ab703009b19916f7d73abe97001d6def24745760b9485103058a122df3
3
+ size 18389259
qrdqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c0402d889eb896d6d674b9e393872b9b013cd65662666d0468b042add506b08
3
- size 18405353
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2ca02aca8aafe7fe2a3bcbc11cda01ac4cd7de57fd1c8999a89fda566ca3706
3
+ size 18388969
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce89df131229debcd89c2cee8e698032c646e7fc35309d76c26d6972a0e0cc9e
3
- size 252552
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e8c07008011ea7e4922b6a6de09b13e7f52fa64a66d87ba4e11bff4bfc5d28b
3
+ size 234706
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 374.0, "std_reward": 214.61360627881913, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-28T22:18:00.700517"}
 
1
+ {"mean_reward": 374.0, "std_reward": 214.89299662855464, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-29T10:24:45.175634"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72697a18adec22ea6400c3fff5eaf39793481eb1547a107aec1164cb53f1ea32
3
- size 27147
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:950112a1661a16b588c666c4ac674b8a66b21e516331e6ebef4dde41310b1fda
3
+ size 42425