Sharing lifelong reinforcement learning knowledge via modulating masks
Lifelong learning agents aim to learn multiple tasks sequentially over a lifetime. This involves the ability to exploit previous knowledge when learning new tasks and to avoid forgetting. Recently, modulating masks, a specific type of parameter isolation approach, have shown promise in both supervised and reinforcement learning. While lifelong learning algorithms have been investigated mainly within a single-agent approach, a question remains on how multiple agents can share lifelong learning knowledge with each other. We show that the parameter isolation mechanism used by modulating masks is particularly suitable for exchanging knowledge among agents in a distributed and decentralized system of lifelong learners. The key idea is that isolating specific task knowledge to specific masks allows agents to transfer only specific knowledge on-demand, resulting in a robust and effective collective of agents. We assume fully distributed and asynchronous scenarios with dynamic agent numbers and connectivity. An on-demand communication protocol ensures agents query their peers for specific masks to be transferred and integrated into their policies when facing each task. Experiments indicate that on-demand mask communication is an effective way to implement distributed and decentralized lifelong reinforcement learning, and provides a lifelong learning benefit with respect to distributed RL baselines such as DD-PPO, IMPALA, and PPO+EWC. The system is particularly robust to connection drops and demonstrates rapid learning due to knowledge exchange.
Defense Advanced Research Projects Agency (DARPA) under Contract No. HR00112190132 (Shared Experience Lifelong Learning)
- Computer Science
Published inProceedings of the Second Conference on Lifelong Learning Agents (CoLLAs 2023)
SourceSecond Conference on Lifelong Learning Agents (CoLLAs 2023)
PublisherML Research Press
- VoR (Version of Record)
Rights holder© The Authors
Publisher statementThis paper appears here with the permission of the conference program committee.
Book seriesProceedings of Machine Learning Research