metadata
library_name: stable-baselines3
tags:
- HumanoidStandup-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
- HumanoidStandup-v4
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: HumanoidStandup-v2
type: HumanoidStandup-v2
metrics:
- type: mean_reward
value: 151147.54 +/- 40669.21
name: mean_reward
verified: false