Upload PPO LunarLander-v2 trained agent
Browse files- README.md +1 -1
- ppo-LunarLander-v2.zip +1 -1
- replay.mp4 +3 -0
- results.json +1 -1
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
|
|
|
10 |
results:
|
11 |
- metrics:
|
12 |
- type: mean_reward
|
13 |
+
value: -123.87 +/- 19.22
|
14 |
name: mean_reward
|
15 |
task:
|
16 |
type: reinforcement-learning
|
ppo-LunarLander-v2.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 140922
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3c254fef95fbbc800b6bf03ba9ce97cf5b098d76139209ae665727bc855bb5b
|
3 |
size 140922
|
replay.mp4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79777bfb3a8ccaec98fa9837c0f9fcf78142fc993e605371fe8aecd437e013ef
|
3 |
+
size 172760
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward": -
|
|
|
1 |
+
{"mean_reward": -123.8688810897991, "std_reward": 19.21930683731547, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-11T22:52:29.860525"}
|