Push Reinforce agent to the Hub
Browse files- README.md +4 -4
- hyperparameters.json +1 -1
- model.pt +2 -2
- replay.mp4 +2 -2
- results.json +1 -1
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
tags:
|
3 |
-
-
|
4 |
- reinforce
|
5 |
- reinforcement-learning
|
6 |
- custom-implementation
|
@@ -10,14 +10,14 @@ model-index:
|
|
10 |
results:
|
11 |
- metrics:
|
12 |
- type: mean_reward
|
13 |
-
value:
|
14 |
name: mean_reward
|
15 |
task:
|
16 |
type: reinforcement-learning
|
17 |
name: reinforcement-learning
|
18 |
dataset:
|
19 |
-
name:
|
20 |
-
type:
|
21 |
---
|
22 |
|
23 |
# **Reinforce** Agent playing **CartPole-v1**
|
|
|
1 |
---
|
2 |
tags:
|
3 |
+
- CartPole-v1
|
4 |
- reinforce
|
5 |
- reinforcement-learning
|
6 |
- custom-implementation
|
|
|
10 |
results:
|
11 |
- metrics:
|
12 |
- type: mean_reward
|
13 |
+
value: 70.60 +/- 24.99
|
14 |
name: mean_reward
|
15 |
task:
|
16 |
type: reinforcement-learning
|
17 |
name: reinforcement-learning
|
18 |
dataset:
|
19 |
+
name: CartPole-v1
|
20 |
+
type: CartPole-v1
|
21 |
---
|
22 |
|
23 |
# **Reinforce** Agent playing **CartPole-v1**
|
hyperparameters.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"h_size":
|
|
|
1 |
+
{"h_size": 16, "n_training_episodes": 1000, "n_evaluation_episodes": 10, "max_t": 1000, "gamma": 1.0, "lr": 0.01, "env_id": "CartPole-v1", "state_space": 4, "action_space": 2}
|
model.pt
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:f1693c3289cc3f3afbb39619ca778cdcc2bd774abed8dd9fd474a454066ddba0
|
3 |
+
size 2591
|
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:f5f6198e78f15ef533c9b87d7f4aa302f8c8989f4d025f45c5462a7bbb0303a6
|
3 |
+
size 10432
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"env_id": "
|
|
|
1 |
+
{"env_id": "CartPole-v1", "mean_reward": 70.6, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-10T15:31:40.756290"}
|