CARoL: Context-aware Adaptation for Robot Learning

TL;DR

CARoL introduces a context-aware framework that leverages prior knowledge to improve the efficiency of reinforcement learning in robotic tasks by analyzing system dynamics and adapting relevant knowledge pieces.

Contribution

The paper presents a novel framework, CARoL, that adaptively integrates prior knowledge into RL for robotic learning, applicable across various RL algorithms and validated on both simulated and real robots.

Findings

CARoL achieves faster convergence and higher rewards in simulation environments.

CARoL enables real-world robots to adapt policies learned in simulation efficiently.

The framework is broadly applicable across different RL algorithms.

Abstract

Using Reinforcement Learning (RL) to learn new robotic tasks from scratch is often inefficient. Leveraging prior knowledge has the potential to significantly enhance learning efficiency, which, however, raises two critical challenges: how to determine the relevancy of existing knowledge and how to adaptively integrate them into learning a new task. In this paper, we propose Context-aware Adaptation for Robot Learning (CARoL), a novel framework to efficiently learn a similar but distinct new task from prior knowledge. CARoL incorporates context awareness by analyzing state transitions in system dynamics to identify similarities between the new task and prior knowledge. It then utilizes these identified similarities to prioritize and adapt specific knowledge pieces for the new task. Additionally, CARoL has a broad applicability spanning policy-based, value-based, and actor-critic RL algorithms. We validate the efficiency and generalizability of CARoL on both simulated robotic platforms and physical ground vehicles. The simulations include CarRacing and LunarLander environments, where CARoL demonstrates faster convergence and higher rewards when learning policies for new tasks. In real-world experiments, we show that CARoL enables a ground vehicle to quickly and efficiently adapt policies learned in simulation to smoothly traverse real-world off-road terrain.