Upload PPO LunarLander-v2 trained baseline agent
Browse files- README.md +2 -1
- ppo3-LunarLander-v2.zip +1 -1
- 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
|
@@ -24,6 +24,7 @@ model-index:
|
|
24 |
|
25 |
|
26 |
|
|
|
27 |
# **PPO** Agent playing **LunarLander-v2**
|
28 |
This is a trained model of a **PPO** agent playing **LunarLander-v2**
|
29 |
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
|
|
10 |
results:
|
11 |
- metrics:
|
12 |
- type: mean_reward
|
13 |
+
value: 291.42 +/- 16.47
|
14 |
name: mean_reward
|
15 |
task:
|
16 |
type: reinforcement-learning
|
|
|
24 |
|
25 |
|
26 |
|
27 |
+
|
28 |
# **PPO** Agent playing **LunarLander-v2**
|
29 |
This is a trained model of a **PPO** agent playing **LunarLander-v2**
|
30 |
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
ppo3-LunarLander-v2.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 142911
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f0fb44425e7f1042d2b9e81f75b72e2d20ff04d57ebb4ac3a6f2e2a92ef6db0
|
3 |
size 142911
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 291.4193619316618, "std_reward": 16.47393064310555, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-28T22:28:40.768240"}
|