Benchmarking Deep Reinforcement Learning for Continuous Control

22 Apr 2016Yan DuanXi ChenRein HouthooftJohn SchulmanPieter Abbeel

Recently, researchers have made significant progress combining the advances in deep learning for learning feature representations with reinforcement learning. Some notable examples include training agents to play Atari games based on raw pixel data and to acquire advanced manipulation skills using raw sensory inputs... (read more)

PDF Abstract

Evaluation results from the paper


  Submit results from this paper to get state-of-the-art GitHub badges and help community compare results to other papers.