Memory-based Reinforcement Learning: Converging with Less Data and Less Real Time

Prioritized Sweeping is a new algorithm for efficient prediction and control of stochastic Markov systems. Incremental learning methods such as Temporal Differencing and Q-learning have fast real time performance. Classical methods are slower, but more accurate, because they make full use of the observations. Prioritized Sweeping aims for the best of both worlds. It uses all previous experiences both to prioritize important dynamic programming sweeps and to guide the exploration of state-space. We compare Prioritized Sweeping with other reinforcement learning schemes for a number of different stochastic optimal control problems. It successfully solves large state-space real time problems with which other methods have difficulty.