Hugging Face's logo

Kastakin
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
Kastakin commited on
Commit
01f36db
•
1 Parent(s): c282024

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +3 -3
  2. args.yml +1 -1
  3. config.yml +2 -2
  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: 663.00 +/- 200.06
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -62,12 +62,12 @@ OrderedDict([('batch_size', 32),
62
  ('env_wrapper',
63
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
64
  ('exploration_final_eps', 0.01),
65
- ('exploration_fraction', 0.1),
66
  ('frame_stack', 4),
67
  ('gradient_steps', 1),
68
  ('learning_rate', 0.0001),
69
  ('learning_starts', 100000),
70
- ('n_timesteps', 1000000.0),
71
  ('optimize_memory_usage', False),
72
  ('policy', 'CnnPolicy'),
73
  ('target_update_interval', 1000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 986.00 +/- 315.59
20
  name: mean_reward
21
  verified: false
22
  ---
 
62
  ('env_wrapper',
63
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
64
  ('exploration_final_eps', 0.01),
65
+ ('exploration_fraction', 0.25),
66
  ('frame_stack', 4),
67
  ('gradient_steps', 1),
68
  ('learning_rate', 0.0001),
69
  ('learning_starts', 100000),
70
+ ('n_timesteps', 3000000.0),
71
  ('optimize_memory_usage', False),
72
  ('policy', 'CnnPolicy'),
73
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 2664546145
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 4292374201
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -8,7 +8,7 @@
8
  - - exploration_final_eps
9
  - 0.01
10
  - - exploration_fraction
11
- - 0.1
12
  - - frame_stack
13
  - 4
14
  - - gradient_steps
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 1000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
8
  - - exploration_final_eps
9
  - 0.01
10
  - - exploration_fraction
11
+ - 0.25
12
  - - frame_stack
13
  - 4
14
  - - gradient_steps
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 3000000.0
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:f5189d0815a3bc3e90d4265784c0cb8add1a1b1e4d744cf9c0babaf3497196c4
3
- size 27224788
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0efa784b89ff6d2a24e28aac9542993b411a386b6da7abff7286342f052c0ba5
3
+ size 27224804
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 sha256:8bfa7177640757b82691b426810db5e50a25097499bd428dc2c611a63a728693
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:353668f17e0a9602546bb2b58c42f8737986c255ca7d19e082b6d6277cbe530b
3
  size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41b0a77de8adde75140c549274d3e1d92edf5e974f6b7a82e466ee9171a37c7c
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e139394ac0781d77db7cbff0a948e67eae55caf3e1fcb18143c3bc397dc57fc
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aec9805919bfd0fcfb97fa41c45d9004ade34e6ffc30aa3b00eab5d8a25045b4
3
- size 192057
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03d08edfe13e81b11ecc4c439f9bf17786211ff4267c4d091539332f870ec409
3
+ size 195752
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 663.0, "std_reward": 200.0649894409314, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-20T14:02:57.912117"}
 
1
+ {"mean_reward": 986.0, "std_reward": 315.593092446587, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-20T16:02:48.635375"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de956eae113bb48f8b9ee9835e6bb0169a2aa33e4dc7c2e5dfb96b6c87be2707
3
- size 36539
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf4e2a53992b6f9b6e2053c56a4191ab1d292ab174bd7277bb3ca01c9d12f0e2
3
+ size 48864