CADENT: Gated Hybrid Distillation for Sample-Efficient Transfer in Reinforcement Learning

TL;DR

CADENT introduces an experience-gated distillation framework that combines strategic automaton knowledge with tactical policies, significantly improving sample efficiency and adaptability in reinforcement learning tasks.

Contribution

It unifies automaton-based and policy distillation methods with a dynamic trust mechanism for better transfer learning in RL.

Findings

Achieves 40-60% better sample efficiency than baselines.

Maintains superior asymptotic performance across environments.

Effective in both sparse-reward and continuous control tasks.

Abstract

Transfer learning promises to reduce the high sample complexity of deep reinforcement learning (RL), yet existing methods struggle with domain shift between source and target environments. Policy distillation provides powerful tactical guidance but fails to transfer long-term strategic knowledge, while automaton-based methods capture task structure but lack fine-grained action guidance. This paper introduces Context-Aware Distillation with Experience-gated Transfer (CADENT), a framework that unifies strategic automaton-based knowledge with tactical policy-level knowledge into a coherent guidance signal. CADENT's key innovation is an experience-gated trust mechanism that dynamically weighs teacher guidance against the student's own experience at the state-action level, enabling graceful adaptation to target domain specifics. Across challenging environments, from sparse-reward grid worlds to continuous control tasks, CADENT achieves 40-60\% better sample efficiency than baselines while maintaining superior asymptotic performance, establishing a robust approach for adaptive knowledge transfer in RL.