---
library_name: stable-baselines3
tags:
- InvertedDoublePendulum-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
- InvertedDoublePendulum-v4
model-index:
- name: PPO
  results:
  - task:
      type: reinforcement-learning
      name: reinforcement-learning
    dataset:
      name: InvertedDoublePendulum-v2
      type: InvertedDoublePendulum-v2
    metrics:
    - type: mean_reward
      value: 6480.49 +/- 2508.74
      name: mean_reward
      verified: false
---