Plug and Play, Model-Based Reinforcement Learning

TL;DR

This paper introduces Plug and Play Markov Decision Processes, an object-based reinforcement learning framework that enables zero-shot object integration and efficient transfer learning for complex scenes.

Contribution

It presents a novel object-based representation allowing zero-shot object integration and efficient reward transfer in reinforcement learning environments.

Findings

Achieves sample-efficiency in various setups.

Enables zero-shot integration of new objects.

Handles addition/removal of objects efficiently.

Abstract

Sample-efficient generalisation of reinforcement learning approaches have always been a challenge, especially, for complex scenes with many components. In this work, we introduce Plug and Play Markov Decision Processes, an object-based representation that allows zero-shot integration of new objects from known object classes. This is achieved by representing the global transition dynamics as a union of local transition functions, each with respect to one active object in the scene. Transition dynamics from an object class can be pre-learnt and thus would be ready to use in a new environment. Each active object is also endowed with its reward function. Since there is no central reward function, addition or removal of objects can be handled efficiently by only updating the reward functions of objects involved. A new transfer learning mechanism is also proposed to adapt reward function in such cases. Experiments show that our representation can achieve sample-efficiency in a variety of set-ups.