sofiaoliveira commited on
Commit
fae2b9e
1 Parent(s): ddac063

Initial commit

Browse files
README.md CHANGED
@@ -10,7 +10,7 @@ model-index:
10
  results:
11
  - metrics:
12
  - type: mean_reward
13
- value: 559.00 +/- 191.67
14
  name: mean_reward
15
  task:
16
  type: reinforcement-learning
@@ -51,16 +51,16 @@ python -m utils.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs
51
  ## Hyperparameters
52
  ```python
53
  OrderedDict([('batch_size', 32),
54
- ('buffer_size', 100000),
55
  ('env_wrapper',
56
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
57
- ('exploration_final_eps', 0.01),
58
  ('exploration_fraction', 0.1),
59
  ('frame_stack', 4),
60
  ('gradient_steps', 1),
61
  ('learning_rate', 0.0001),
62
- ('learning_starts', 100000),
63
- ('n_timesteps', 1000000.0),
64
  ('optimize_memory_usage', False),
65
  ('policy', 'CnnPolicy'),
66
  ('target_update_interval', 1000),
 
10
  results:
11
  - metrics:
12
  - type: mean_reward
13
+ value: 340.50 +/- 183.40
14
  name: mean_reward
15
  task:
16
  type: reinforcement-learning
 
51
  ## Hyperparameters
52
  ```python
53
  OrderedDict([('batch_size', 32),
54
+ ('buffer_size', 10000),
55
  ('env_wrapper',
56
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
57
+ ('exploration_final_eps', 0.05),
58
  ('exploration_fraction', 0.1),
59
  ('frame_stack', 4),
60
  ('gradient_steps', 1),
61
  ('learning_rate', 0.0001),
62
+ ('learning_starts', 1000),
63
+ ('n_timesteps', 100000.0),
64
  ('optimize_memory_usage', False),
65
  ('policy', 'CnnPolicy'),
66
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -50,7 +50,7 @@
50
  - - save_replay_buffer
51
  - false
52
  - - seed
53
- - 1990164280
54
  - - storage
55
  - null
56
  - - study_name
 
50
  - - save_replay_buffer
51
  - false
52
  - - seed
53
+ - 1867981740
54
  - - storage
55
  - null
56
  - - study_name
config.yml CHANGED
@@ -2,11 +2,11 @@
2
  - - - batch_size
3
  - 32
4
  - - buffer_size
5
- - 100000
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
@@ -16,9 +16,9 @@
16
  - - learning_rate
17
  - 0.0001
18
  - - learning_starts
19
- - 100000
20
  - - n_timesteps
21
- - 1000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
2
  - - - batch_size
3
  - 32
4
  - - buffer_size
5
+ - 10000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
9
+ - 0.05
10
  - - exploration_fraction
11
  - 0.1
12
  - - frame_stack
 
16
  - - learning_rate
17
  - 0.0001
18
  - - learning_starts
19
+ - 1000
20
  - - n_timesteps
21
+ - 100000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f98e74e62cdab2823769c6aed1505ea7710a6005a33412dabe647da08ec61d08
3
- size 27224878
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a0eea622eca69f7e5eb493892b38ab3a1af1e54341ff4c2e2b1b1ef7df4c88c
3
+ size 27224870
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:b1c39ecfd6187318998499be43ee6d3f26a50de69f1d6a85b34c190e93e31656
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c4a1c0e8b6782d65681fb548fc0c04dfd5e5c020f7c1142be90d36310cbc13a
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:f8ee52fbe0fa9eb1c6946e372779e6caacf722849ee01707c16e4b4bac046c1c
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00d0a4debcef5030a231816ce2df39d9dea5f6be114c3ea281967a39508bf9e5
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:430e1f7bf7dc2b093acf6af56f597b4cc588bd3bbd413cf630f138b97c91745e
3
- size 204372
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a682e254418b17aebcda4a89b1d6bb823bb04da20916ea178e73845c18fabb9
3
+ size 229245
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 559.0, "std_reward": 191.67420275039623, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-08-10T11:04:48.844042"}
 
1
+ {"mean_reward": 340.5, "std_reward": 183.40460735761246, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-08-10T11:51:50.836497"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bac3bf3adf804eaeb27c5ed5375edb915cdc8318e724bd8737eef186888f7435
3
- size 36195
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ad8d421616e587c8a91ac0b2442c91165643bbf25c7787efe11c20c121585ae
3
+ size 5006