FORK: A FORward-looKing Actor for Model-Free Reinforcement Learning

Honghao Wei, Lei Ying

Keywords: Reinforcement Learning, Actor Critic, Policy Gradient, Model Free

Abstract: In this paper, we propose a new type of Actor, named forward-looking Actor or FORK for short, for Actor-Critic algorithms. FORK can be easily integrated into a model-free Actor-Critic algorithm. Our experiments on six Box2D and MuJoCo environments with continuous state and action spaces demonstrate significant performance improvement FORK can bring to the state-of-the-art algorithms. A variation of FORK can further solve BipedalWalkerHardcore in as few as four hours using a single GPU.

One-sentence Summary: A new type of actor named forward-looking actor or FORK for short, for Actor-Critic reinforcement learning algorithms.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Community Implementations: [ 6 code implementations](https://www.catalyzex.com/paper/arxiv:2010.01652/code)

Reviewed Version (pdf): https://openreview.net/references/pdf?id=WXlWcTSkT4