Joint Perception and Control as Inference with an Object-based Implementation

2019/03/04 by Li, Minne, Tian, Zheng, Nashikkar, Pranav +3
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · doi:10.48550/arxiv.1903.01385

Abstract

Existing model-based reinforcement learning methods often study perception modeling and decision making separately. We introduce joint Perception and Control as Inference (PCI), a general framework to combine perception and control for partially observable environments through Bayesian inference. Based on the fact that object-level inductive biases are critical in human perceptual learning and reasoning, we propose Object-based Perception Control (OPC), an instantiation of PCI which manages to facilitate control using automatic discovered object-based representations. We develop an unsupervised end-to-end solution and analyze the convergence of the perception model update. Experiments in a high-dimensional pixel environment demonstrate the learning effectiveness of our object-based perception control approach. Specifically, we show that OPC achieves good perceptual grouping quality and outperforms several strong baselines in accumulated rewards.

Related

• Perception Learning: A Formal Separation of Sensory Representation Learning from Decision Learning
• ROLL: Visual Self-Supervised Reinforcement Learning with Object Reasoning
• Learning to Perceive in Deep Model-Free Reinforcement Learning
• Perception-R1: Pioneering Perception Policy with Reinforcement Learning
• Structured World Belief for Reinforcement Learning in POMDP