Gaussian Processes for Sample Efficient Reinforcement Learning with RMAX-Like Exploration

Abstract. We present an implementation of model-based online reinforcement learning (RL) for continuous domains with deterministic transitions that is specifically designed to achieve low sample complexity. To achieve low sample complexity, since the environment is unknown, an agent must intelligently balance exploration and exploitation, and must be able to rapidly generalize from observations. While in the past a number of related sample efficient RL algorithms have been proposed, to allow theoretical analysis, mainly model-learners with weak generalization capabilities were considered. Here, we separate function approximation in the model learner (which does require samples) from the interpolation in the planner (which does not require samples). For model-learning we apply Gaussian processes regression (GP) which is able to automatically adjust itself to the complexity of the problem (via Bayesian hyperparameter selection) and, in practice, often able to learn a highly accurate mode...

• Type: Journal
• Year: 2010
• Where: PKDD
• Authors: Tobias Jung, Peter Stone
• Keywords: Data Mining, Low Sample Complexity, Model-based Online Reinforcement, PKDD 2010, Sample Efficient Rl