metadata
library_name: stable-baselines3
tags:
- InvertedPendulum-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
- InvertedPendulum-v4
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: InvertedPendulum-v2
type: InvertedPendulum-v2
metrics:
- type: mean_reward
value: 11.20 +/- 0.98
name: mean_reward
verified: false