Learning Approximate Stochastic Transition Models

2017/10/26 by Yuhang Song, Christopher Grimm, Song, Yuhang +5 · 1 citation
Computer Science · Physics and Astronomy · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Model Reduction and Neural Networks #Neural Networks and Applications #Reinforcement Learning in Robotics

paper · pdf · doi:10.48550/arxiv.1710.09718

openalex publication_date 2017/10/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We examine the problem of learning mappings from state to state, suitable for use in a model-based reinforcement-learning setting, that simultaneously generalize to novel states and can capture stochastic transitions. We show that currently popular generative adversarial networks struggle to learn these stochastic transition models but a modification to their loss functions results in a powerful learning algorithm for this class of problems.

Cited by

• Diversity-Driven Extensible Hierarchical Reinforcement Learning

Related

• Learning Multimodal Transition Dynamics for Model-Based Reinforcement Learning
• Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networks
• Path to Stochastic Stability: Comparative Analysis of Stochastic Learning Dynamics in Games
• Multimodal Transitions for Generative Stochastic Networks
• Learning invariant representations of time-homogeneous stochastic dynamical systems