Mixture-of-Experts Meets In-Context Reinforcement Learning

TL;DR

This paper introduces T2MIR, a novel transformer architecture incorporating token-wise and task-wise mixture-of-experts to improve in-context reinforcement learning across diverse tasks and data modalities.

Contribution

The paper proposes T2MIR, an innovative MoE-based framework that enhances in-context RL by capturing multi-modal semantics and managing task heterogeneity with contrastive routing.

Findings

T2MIR significantly improves in-context learning performance.

It outperforms various baseline models.

The approach effectively handles diverse decision tasks.

Abstract

In-context reinforcement learning (ICRL) has emerged as a promising paradigm for adapting RL agents to downstream tasks through prompt conditioning. However, two notable challenges remain in fully harnessing in-context learning within RL domains: the intrinsic multi-modality of the state-action-reward data and the diverse, heterogeneous nature of decision tasks. To tackle these challenges, we propose T2MIR (Token- and Task-wise MoE for In-context RL), an innovative framework that introduces architectural advances of mixture-of-experts (MoE) into transformer-based decision models. T2MIR substitutes the feedforward layer with two parallel layers: a token-wise MoE that captures distinct semantics of input tokens across multiple modalities, and a task-wise MoE that routes diverse tasks to specialized experts for managing a broad task distribution with alleviated gradient conflicts. To enhance task-wise routing, we introduce a contrastive learning method that maximizes the mutual information between the task and its router representation, enabling more precise capture of task-relevant information. The outputs of two MoE components are concatenated and fed into the next layer. Comprehensive experiments show that T2MIR significantly facilitates in-context learning capacity and outperforms various types of baselines. We bring the potential and promise of MoE to ICRL, offering a simple and scalable architectural enhancement to advance ICRL one step closer toward achievements in language and vision communities. Our code is available at https://github.com/NJU-RL/T2MIR.