Train with 2.5M episodes and gamma 0.96
Browse files- q-learning.pkl +1 -1
- replay.mp4 +0 -0
- results.json +1 -1
q-learning.pkl
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 24572
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a561c70fdca7962290ff0d5086f75b3fe2265ec6df0a929678aefa607f0fd568
|
| 3 |
size 24572
|
replay.mp4
CHANGED
|
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
|
results.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2023-06-30T14:
|
|
|
|
| 1 |
+
{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2023-06-30T14:37:16.515457"}
|