Progressive Reinforcement Learning with Distillation for Multi-Skilled Motion Control
ICLR, Volume abs/1802.04765, 2018.
Deep reinforcement learning has demonstrated increasing capabilities for continuous control problems, including agents that can move with skill and agility through their environment. An open problem in this setting is that of developing good strategies for integrating or merging policies for multiple skills, where each individual skill is...More
PPT (Upload PPT)