Dynamics-adaptive Continual Reinforcement Learning Via Progressive Contextualization

Abstract

A key challenge of continual reinforcement learning (CRL) in dynamic environments is to promptly adapt the RL agent's behavior as the environment changes over its lifetime, while minimizing the catastrophic forgetting of the learned information. To address this challenge, in this article, we propose DaCoRL, i.e., dynamics-adaptive continual RL. DaCoRL learns a context-conditioned policy using progressive contextualization, which incrementally clusters a stream of stationary tasks in the dynamic environment into a series of contexts and opts for an expandable multihead neural network to approximate the policy. Specifically, we define a set of tasks with similar dynamics as an environmental context and formalize context inference as a procedure of online Bayesian infinite Gaussian mixture clustering on environment features, resorting to online Bayesian inference to infer the posterior distribution over contexts. Under the assumption of a Chinese restaurant process prior, this technique c

Stats

• citations8
• S2 citations—
• github stars0
• HF likes0
• heat score7.16
• arxiv keyzhang2022dynamics

Related papers

• Demonstration-guided Continual Reinforcement Learning In Dynamic Environments (2025)0.00
• Online Reinforcement Learning In Non-stationary Context-driven Environments (2023)0.00
• Continual Policy Distillation From Distributed Reinforcement Learning Teachers (2026)0.00
• Contextual Intelligence The Next Leap For Reinforcement Learning (2026)0.00
• Adaptive Action Duration With Contextual Bandits For Deep Reinforcement Learning In Dynamic Environments (2025)0.00
• Action-adaptive Continual Learning: Enabling Policy Generalization Under Dynamic Action Spaces (2025)0.00
• Reinforcement Learning In Presence Of Discrete Markovian Context Evolution (2022)0.00
• Multi-agent Continual Coordination Via Progressive Task Contextualization (2023)5.24