Incremental Learning of Planning Actions in Model-Based Reinforcement Learning

Incremental Learning of Planning Actions in Model-Based Reinforcement Learning

Jun Hao Alvin Ng, Ronald P. A. Petrick

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence
Main track. Pages 3195-3201. https://doi.org/10.24963/ijcai.2019/443

The soundness and optimality of a plan depends on the correctness of the domain model. Specifying complete domain models can be difficult when interactions between an agent and its environment are complex. We propose a model-based reinforcement learning (MBRL) approach to solve planning problems with unknown models. The model is learned incrementally over episodes using only experiences from the current episode which suits non-stationary environments. We introduce the novel concept of reliability as an intrinsic motivation for MBRL, and a method to learn from failure to prevent repeated instances of similar failures. Our motivation is to improve the learning efficiency and goal-directedness of MBRL. We evaluate our work with experimental results for three planning domains.
Keywords:
Machine Learning: Reinforcement Learning
Planning and Scheduling: Planning Algorithms
Knowledge Representation and Reasoning: Action, Change and Causality