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 +1 -1
- 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
|
|
@@ -60,7 +60,7 @@ OrderedDict([('batch_size', 32),
|
|
| 60 |
('gradient_steps', 1),
|
| 61 |
('learning_rate', 0.0001),
|
| 62 |
('learning_starts', 100000),
|
| 63 |
-
('n_timesteps',
|
| 64 |
('optimize_memory_usage', True),
|
| 65 |
('policy', 'CnnPolicy'),
|
| 66 |
('target_update_interval', 1000),
|
|
|
|
| 10 |
results:
|
| 11 |
- metrics:
|
| 12 |
- type: mean_reward
|
| 13 |
+
value: 784.00 +/- 298.23
|
| 14 |
name: mean_reward
|
| 15 |
task:
|
| 16 |
type: reinforcement-learning
|
|
|
|
| 60 |
('gradient_steps', 1),
|
| 61 |
('learning_rate', 0.0001),
|
| 62 |
('learning_starts', 100000),
|
| 63 |
+
('n_timesteps', 3000000.0),
|
| 64 |
('optimize_memory_usage', True),
|
| 65 |
('policy', 'CnnPolicy'),
|
| 66 |
('target_update_interval', 1000),
|
args.yml
CHANGED
|
@@ -50,7 +50,7 @@
|
|
| 50 |
- - save_replay_buffer
|
| 51 |
- false
|
| 52 |
- - seed
|
| 53 |
-
-
|
| 54 |
- - storage
|
| 55 |
- null
|
| 56 |
- - study_name
|
|
|
|
| 50 |
- - save_replay_buffer
|
| 51 |
- false
|
| 52 |
- - seed
|
| 53 |
+
- 2905456109
|
| 54 |
- - storage
|
| 55 |
- null
|
| 56 |
- - study_name
|
config.yml
CHANGED
|
@@ -18,7 +18,7 @@
|
|
| 18 |
- - learning_starts
|
| 19 |
- 100000
|
| 20 |
- - n_timesteps
|
| 21 |
-
-
|
| 22 |
- - optimize_memory_usage
|
| 23 |
- true
|
| 24 |
- - policy
|
|
|
|
| 18 |
- - learning_starts
|
| 19 |
- 100000
|
| 20 |
- - n_timesteps
|
| 21 |
+
- 3000000.0
|
| 22 |
- - optimize_memory_usage
|
| 23 |
- true
|
| 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 sha256:09d7ea893b5fa34c84c8431c30fd5618b0670206752cf36757459845cacb9502
|
| 3 |
+
size 27222203
|
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 13503145
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6d92d2c1441253744f59e83c146ddd176b3d84a75f32dfefc9d2262a16530b5
|
| 3 |
size 13503145
|
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 sha256:609d976f2d42484f6cb422c6d7792d7bd37158418792af0d8f029e91d31348be
|
| 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 sha256:3459baac36f20e9bf2da4c19773b6e70f40b5acd4658a33ee129e79eaee14c03
|
| 3 |
+
size 225890
|
results.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"mean_reward":
|
|
|
|
| 1 |
+
{"mean_reward": 784.0, "std_reward": 298.22642404723297, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-06-27T05:49:28.738973"}
|
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:d539444f20b823e01a7375f000f485b1db15b4aa1ec259df2dbb153d25a3f7a9
|
| 3 |
+
size 91196
|