zikunukiz / baselines

Algorithms for RL Generalization with Surprise Minimization

https://arxiv.org/abs/2004.12399

generalization reinforcement-learning

Algorithms (ppo2, ppo2_normal, ppo2_cvae) for: https://github.com/chenziku/train-procgen

About

Algorithms for RL Generalization with Surprise Minimization

https://arxiv.org/abs/2004.12399

generalization reinforcement-learning

Languages

Language:Python 100.0%