Sharing Lifelong Reinforcement Learning Knowledge via Modulating Masks

by   Saptarshi Nath, et al.

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. Modulating masks, a specific type of parameter isolation approach, have recently 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 the isolation of specific task knowledge to specific masks allows agents to transfer only specific knowledge on-demand, resulting in robust and effective distributed lifelong learning. 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 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.


page 8

page 24

page 25


Lifelong Reinforcement Learning with Modulating Masks

Lifelong learning aims to create AI systems that continuously and increm...

DDA3C: Cooperative Distributed Deep Reinforcement Learning in A Group-Agent System

It can largely benefit the reinforcement learning process of each agent ...

KnowSR: Knowledge Sharing among Homogeneous Agents in Multi-agent Reinforcement Learning

Recently, deep reinforcement learning (RL) algorithms have made great pr...

Lightweight Learner for Shared Knowledge Lifelong Learning

In Lifelong Learning (LL), agents continually learn as they encounter ne...

Scaling Distributed Multi-task Reinforcement Learning with Experience Sharing

Recently, DARPA launched the ShELL program, which aims to explore how ex...

Separation of Concerns in Reinforcement Learning

In this paper, we propose a framework for solving a single-agent task by...

Asynchronous Bayesian Learning over a Network

We present a practical asynchronous data fusion model for networked agen...

Please sign up or login with your details

Forgot password? Click here to reset