Learning by Playing - Solving Sparse Reward Tasks from Scratch
This addresses the exploration challenge in sparse reward RL for robotics, representing a novel paradigm rather than an incremental improvement.
The paper tackles the problem of learning complex behaviors from scratch in reinforcement learning with multiple sparse reward signals, achieving success in challenging robotic manipulation settings.
We propose Scheduled Auxiliary Control (SAC-X), a new learning paradigm in the context of Reinforcement Learning (RL). SAC-X enables learning of complex behaviors - from scratch - in the presence of multiple sparse reward signals. To this end, the agent is equipped with a set of general auxiliary tasks, that it attempts to learn simultaneously via off-policy RL. The key idea behind our method is that active (learned) scheduling and execution of auxiliary policies allows the agent to efficiently explore its environment - enabling it to excel at sparse reward RL. Our experiments in several challenging robotic manipulation settings demonstrate the power of our approach.