Knowledge capture, adaptation and composition (KCAC): A framework for cross-task curriculum learning in robotic manipulation

TL;DR

This paper introduces the KCAC framework that enhances robotic manipulation learning by systematically integrating knowledge transfer through cross-task curriculum learning, significantly reducing training time and improving success rates.

Contribution

The paper presents a novel KCAC framework that effectively captures, adapts, and composes knowledge for cross-task curriculum learning in robotic manipulation, addressing existing RL limitations.

Findings

Achieved 40% reduction in training time.

Improved task success rates by 10%.

Identified key curriculum design parameters.

Abstract

Reinforcement learning (RL) has demonstrated remarkable potential in robotic manipulation but faces challenges in sample inefficiency and lack of interpretability, limiting its applicability in real world scenarios. Enabling the agent to gain a deeper understanding and adapt more efficiently to diverse working scenarios is crucial, and strategic knowledge utilization is a key factor in this process. This paper proposes a Knowledge Capture, Adaptation, and Composition (KCAC) framework to systematically integrate knowledge transfer into RL through cross-task curriculum learning. KCAC is evaluated using a two block stacking task in the CausalWorld benchmark, a complex robotic manipulation environment. To our knowledge, existing RL approaches fail to solve this task effectively, reflecting deficiencies in knowledge capture. In this work, we redesign the benchmark reward function by removing rigid constraints and strict ordering, allowing the agent to maximize total rewards concurrently and enabling flexible task completion. Furthermore, we define two self-designed sub-tasks and implement a structured cross-task curriculum to facilitate efficient learning. As a result, our KCAC approach achieves a 40 percent reduction in training time while improving task success rates by 10 percent compared to traditional RL methods. Through extensive evaluation, we identify key curriculum design parameters subtask selection, transition timing, and learning rate that optimize learning efficiency and provide conceptual guidance for curriculum based RL frameworks. This work offers valuable insights into curriculum design in RL and robotic learning.