Gaussian Processes for Sample Efficient Reinforcement Learning with RMAX-like Exploration
This work addresses the problem of high sample complexity in reinforcement learning for continuous domains, offering a method that balances exploration and exploitation, though it is incremental as it builds on existing RMAX-like exploration principles.
The paper tackles sample-efficient reinforcement learning in continuous domains by using Gaussian processes for model learning and separating function approximation from planning, achieving low sample complexity on four benchmark domains.
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 model from very little data. In addition, a GP provides a natural way to determine the uncertainty of its predictions, which allows us to implement the "optimism in the face of uncertainty" principle used to efficiently control exploration. Our method is evaluated on four common benchmark domains.