Particle Swarm Optimization for Model Predictive Control in Reinforcement Learning Environments

This chapter introduces a model-based reinforcement learning (RL) approach for continuous state and action spaces. While most RL methods try to find closed-form policies, the approach taken here employs numerical online optimization of control action sequences following the strategy of nonlinear model predictive control. First, a general method for reformulating RL problems as optimization tasks is provided. Subsequently, particle swarm optimization (PSO) is applied to search for optimal solutions. This PSO policy (PSO-P) is effective for high dimensional state spaces and does not require a priori assumptions about adequate policy representations. Furthermore, by translating RL problems into optimization tasks, the rich collection of real-world-inspired RL benchmarks is made available for benchmarking numerical optimization techniques. The effectiveness of PSO-P is demonstrated on two standard benchmarks mountain car and cart-pole swing-up and a new industry-inspired benchmark, the so-called industrial benchmark.