mlsanityData to 14 Oct 2026

Adapting the Behavior of Reinforcement Learning Agents to Changing Action Spaces and Reward Functions

arXiv 2601.20714 ↗First posted 28 Jan 2026cs.LG cs.AIcited by 0

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

Abstract (arXiv)

Reinforcement Learning (RL) agents often struggle in real-world applications where environmental conditions are non-stationary, particularly when reward functions shift or the available action space expands. This paper introduces MORPHIN, a self-adaptive Q-learning framework that enables on-the-fly adaptation without full retraining. By integrating concept drift detection with dynamic adjustments to learning and exploration hyperparameters, MORPHIN adapts agents to changes in both the reward function and on-the-fly expansions of the agent's action space, while preserving prior policy knowledge to prevent catastrophic forgetting. We validate our approach using a Gridworld benchmark and a traffic signal control simulation. The results demonstrate that MORPHIN achieves superior convergence speed and continuous adaptation compared to a standard Q-learning baseline, improving learning efficiency by up to 1.7x.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 5 of its 18 references that are in the map. First posted on arXiv 28 Jan 2026.

Builds on

5 of 18 references.

References · 5

  1. 2020Towards Continual Reinforcement Learning: A Review and Perspectivescited by 274
  2. 2020A Survey of Reinforcement Learning Algorithms for Dynamically Varying Environmentscited by 62
  3. 2021Self-Adaptive Systems: A Systematic Literature Review Across Categories and Domainscited by 6
  4. 2023First-Explore, then Exploit: Meta-Learning to Solve Hard Exploration-Exploitation Trade-Offscited by 4
  5. 2022A Study of Continual Learning Methods for Q-Learningcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Towards Adapting Reinforcement Learning Agents to New Tasks: Insights from Q-Values
  2. 2025Efficient Adaptation of Reinforcement Learning Agents to Sudden Environmental Change
  3. 2025Behavior-Adaptive Q-Learning: A Unifying Framework for Offline-to-Online RL
  4. 2025Provably Efficient Reward Transfer in Reinforcement Learning with Discrete Markov Decision Processes
  5. 2026Scalable Reinforcement Learning via Adaptive Batch Scaling
  6. 2025Learn to Change the World: Multi-level Reinforcement Learning with Model-Changing Actions
  7. 2025Instance-Dependent Continuous-Time Reinforcement Learning via Maximum Likelihood Estimation
  8. 2026Online Adaptive Reinforcement Learning with Echo State Networks for Non-Stationary Dynamics