Reinforcement and Imitation Learning for Diverse Visuomotor Skills

Citations Over TimeTop 10% of 2018 papers

Abstract

We propose a model-free deep reinforcement learning method that leverages a small amount of demonstration data to assist a reinforcement learning agent. We apply this approach to robotic manipulation tasks and train end-to-end visuomotor policies that map directly from RGB camera inputs to joint velocities. We demonstrate that our approach can solve a wide variety of visuomotor tasks, for which engineering a scripted controller would be laborious. In experiments, our reinforcement and imitation agent achieves significantly better performances than agents trained with reinforcement learning or imitation learning alone. We also illustrate that these policies, trained with large visual and dynamics variations, can achieve preliminary successes in zero-shot sim2real transfer.

Related Papers

• → Deep reinforcement learning based mobile edge computing for intelligent Internet of Things(2020)124 cited
• → REINFORCEMENT OF VOCALIZATIONS THROUGH CONTINGENT VOCAL IMITATION(2011)63 cited
• → Reinforcement control of observational learning in young children: A behavioral analysis of modeling(1988)12 cited
• Effects of imitation training on immediate and delayed imitation by severely retarded children.(1978)
• → Comparison of Nonretarded and Mentally Retarded Children on Tasks Involving Direct and Rule-Governed Imitation(1976)1 cited