Hugging Face's logo

apurva19
/
dqn-SpaceInvadersNoFrameskip-v2

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
apurva19 commited on
Commit
9f6c429
•
1 Parent(s): 41d15cb

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 +2 -2
  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
@@ -10,7 +10,7 @@ model-index:
10
  results:
11
  - metrics:
12
  - type: mean_reward
13
- value: 274.50 +/- 31.50
14
  name: mean_reward
15
  task:
16
  type: reinforcement-learning
@@ -59,8 +59,8 @@ OrderedDict([('batch_size', 32),
59
  ('frame_stack', 4),
60
  ('gradient_steps', 1),
61
  ('learning_rate', 0.0001),
62
- ('learning_starts', 100000),
63
- ('n_timesteps', 100000.0),
64
  ('optimize_memory_usage', False),
65
  ('policy', 'CnnPolicy'),
66
  ('target_update_interval', 1000),
 
10
  results:
11
  - metrics:
12
  - type: mean_reward
13
+ value: 450.50 +/- 137.19
14
  name: mean_reward
15
  task:
16
  type: reinforcement-learning
 
59
  ('frame_stack', 4),
60
  ('gradient_steps', 1),
61
  ('learning_rate', 0.0001),
62
+ ('learning_starts', 10000),
63
+ ('n_timesteps', 1000000.0),
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
- - 844456233
54
  - - storage
55
  - null
56
  - - study_name
 
50
  - - save_replay_buffer
51
  - false
52
  - - seed
53
+ - 145356749
54
  - - storage
55
  - null
56
  - - study_name
config.yml CHANGED
@@ -16,9 +16,9 @@
16
  - - learning_rate
17
  - 0.0001
18
  - - learning_starts
19
- - 100000
20
  - - n_timesteps
21
- - 100000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
16
  - - learning_rate
17
  - 0.0001
18
  - - learning_starts
19
+ - 10000
20
  - - n_timesteps
21
+ - 1000000.0
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:a3e432a71d41a81325ddd05e24267233c0a765aad0399210c760ac9b7c1ccd54
3
- size 13719817
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4243784fcbe4de573e47eebc55a48e0c16c63e3ab3db40a75d9fe29878fc9585
3
+ size 27224877
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 sha256:71a21ae67866ddb856ecbb70c8ba0e04af200cc5da53fbcb90e773d87e996b31
3
- size 687
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2341a6f111a135db403bbca7619b913de87ac73074c24cca5051b0d1e50f5ecc
3
+ size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2dd13dd95d5e71829206da3fce160aeb4a790c04a857be759c1da9cabd599658
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:139430e3ebb4992ba382484bc6d56281a0224332ac1f22673f0fe5706cbde2cc
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e13a11a839fea521ecfd34a27ae00521e04cfb8dd63fb3e005e2d701b498e2b
3
- size 261744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5572f891b3d336cdd1611cef938f7704226e51227b52a31b1e4447eefcbb909
3
+ size 234561
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 274.5, "std_reward": 31.5, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-09-04T09:05:59.855856"}
 
1
+ {"mean_reward": 450.5, "std_reward": 137.19420541699273, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-09-04T14:35:32.973367"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30ccd46c7fb134a63849ec8f69a5bd6e7ef05e5b56b78ef07a5739c3640b2317
3
- size 5798
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:990dec958ea3a1bc479c7e4f6bb951ad65999564c47684d1d03ed8e08e14833b
3
+ size 36711