Continuous Value Iteration (CVI) Reinforcement Learning and Imaginary Experience Replay (IER) for learning multi-goal, continuous action and state space controllers
It addresses multi-goal control for robotics, but appears incremental as it builds on existing RL methods with new techniques.
The paper tackles learning controllers for robots in continuous action, state, and goal spaces, achieving faster and better performance in simulation and real-world tasks.
This paper presents a novel model-free Reinforcement Learning algorithm for learning behavior in continuous action, state, and goal spaces. The algorithm approximates optimal value functions using non-parametric estimators. It is able to efficiently learn to reach multiple arbitrary goals in deterministic and nondeterministic environments. To improve generalization in the goal space, we propose a novel sample augmentation technique. Using these methods, robots learn faster and overall better controllers. We benchmark the proposed algorithms using simulation and a real-world voltage controlled robot that learns to maneuver in a non-observable Cartesian task space.