Initial commit
Browse files- README.md +2 -2
- args.yml +1 -1
- config.yml +1 -1
- dqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
- dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
- dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +2 -2
- dqn-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
- replay.mp4 +2 -2
- results.json +1 -1
- 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:
|
| 14 |
name: mean_reward
|
| 15 |
task:
|
| 16 |
type: reinforcement-learning
|
|
@@ -66,7 +66,7 @@ OrderedDict([('batch_size', 32),
|
|
| 66 |
('gradient_steps', 1),
|
| 67 |
('learning_rate', 0.0001),
|
| 68 |
('learning_starts', 100000),
|
| 69 |
-
('n_timesteps',
|
| 70 |
('optimize_memory_usage', False),
|
| 71 |
('policy', 'CnnPolicy'),
|
| 72 |
('target_update_interval', 1000),
|
|
|
|
| 10 |
results:
|
| 11 |
- metrics:
|
| 12 |
- type: mean_reward
|
| 13 |
+
value: 701.50 +/- 210.88
|
| 14 |
name: mean_reward
|
| 15 |
task:
|
| 16 |
type: reinforcement-learning
|
|
|
|
| 66 |
('gradient_steps', 1),
|
| 67 |
('learning_rate', 0.0001),
|
| 68 |
('learning_starts', 100000),
|
| 69 |
+
('n_timesteps', 1000000.0),
|
| 70 |
('optimize_memory_usage', False),
|
| 71 |
('policy', 'CnnPolicy'),
|
| 72 |
('target_update_interval', 1000),
|
args.yml
CHANGED
|
@@ -54,7 +54,7 @@
|
|
| 54 |
- - save_replay_buffer
|
| 55 |
- false
|
| 56 |
- - seed
|
| 57 |
-
-
|
| 58 |
- - storage
|
| 59 |
- null
|
| 60 |
- - study_name
|
|
|
|
| 54 |
- - save_replay_buffer
|
| 55 |
- false
|
| 56 |
- - seed
|
| 57 |
+
- 1560685340
|
| 58 |
- - storage
|
| 59 |
- null
|
| 60 |
- - study_name
|
config.yml
CHANGED
|
@@ -18,7 +18,7 @@
|
|
| 18 |
- - learning_starts
|
| 19 |
- 100000
|
| 20 |
- - n_timesteps
|
| 21 |
-
-
|
| 22 |
- - optimize_memory_usage
|
| 23 |
- false
|
| 24 |
- - policy
|
|
|
|
| 18 |
- - learning_starts
|
| 19 |
- 100000
|
| 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:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c7b7d9b74f451e52a6e5da5be8eafc5544c683a1bfb0d81f972c2a46134ae65
|
| 3 |
+
size 27224829
|
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:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:472d071840e12961bc82d791e2a98510b0620ba6aed802324b2978212648d828
|
| 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:
|
| 3 |
size 13504937
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b70c8848dbd0621e97e34a89661d6233587bde27f12f797b7c1c4a9c57aba0f
|
| 3 |
size 13504937
|
replay.mp4
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7634b98e7e70369eb63f1e161dab6811b0514506b6e906a9fb1e0598fc7ab284
|
| 3 |
+
size 181082
|
results.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"mean_reward":
|
|
|
|
| 1 |
+
{"mean_reward": 701.5, "std_reward": 210.87970504531725, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-29T17:10:30.322872"}
|
train_eval_metrics.zip
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2500ebcd85347f2f6a0e41347250167ef8ce810caabe37e6fb4e5e6824ad008
|
| 3 |
+
size 38118
|