Research Area:  Machine Learning
In this paper we study how to learn stochastic, multimodal transition dynamics in reinforcement learning (RL) tasks. We focus on evaluating transition function estimation, while we defer planning over this model to future work. Stochasticity is a fundamental property of many task environments. However, discriminative function approximators have difficulty estimating multimodal stochasticity. In contrast, deep generative models do capture complex high-dimensional outcome distributions. First we discuss why, amongst such models, conditional variational inference (VI) is theoretically most appealing for model-based RL. Subsequently, we compare different VI models on their ability to learn complex stochasticity on simulated functions, as well as on a typical RL gridworld with multimodal dynamics. Results show VI successfully predicts multimodal outcomes, but also robustly ignores these for deterministic parts of the transition dynamics. In summary, we show a robust method to learn multimodal transitions using function approximation, which is a key preliminary for model-based RL in stochastic domains.
Keywords:  
multimodal transition
Reinforcement Learning
deep generative models
variational inference
Machine Learning
Author(s) Name:  Thomas M. Moerland, Joost Broekens, Catholijn M. Jonker
Journal name:  Machine Learning
Conferrence name:  
Publisher name:  arXiv:1705.00470
DOI:  https://doi.org/10.48550/arXiv.1705.00470
Volume Information:  version, v2
Paper Link:   https://arxiv.org/abs/1705.00470