Action-Adaptive Continual Learning: Enabling Policy Generalization under Dynamic Action Space

Chaofan Pan, Jiafen Liu, Yanhua Li, Linbo Xiong, Fan Min, Wei Wei, Xin YangOpenReview 2026 · Submission to ICLR 2026 · Rejected · OpenReview

Abstract

Continual Learning (CL) is a romising paradigm that enables agents to learn a sequence of tasks, accumulating knowledge learned in the past and using it for problem-solving or future task learning. However, existing CL methods often assume that the agent’s capabilities remain static within dynamic environments, which doesn’t reflect real-world scenarios where capabilities dynamically change. This paper introduces a new and realistic problem: *Continual Learning with Dynamic Capabilities* (CL-DC), posing a significant challenge for CL agents: How can policy generalization across different action spaces be achieved? Inspired by the cortical functions, we propose an **A**ction-**A**daptive **C**ontinual **L**earning framework (AACL) to address this challenge. Our framework decouples the agent’s policy from the specific action space by building an action representation space. For a new action space, the encoder-decoder of action representations is adaptively fine-tuned to maintain a balance between stability and plasticity. Furthermore, we release a benchmark based on three environments to validate the effectiveness of methods for CL-DC. Experimental results demonstrate that our framework outperforms popular methods by generalizing the policy across action spaces.
BibTeX
@misc{pan2026action,
  author = {Chaofan Pan and Jiafen Liu and Yanhua Li and Linbo Xiong and Fan Min and Wei Wei and Xin Yang},
  title = {{Action-Adaptive Continual Learning: Enabling Policy Generalization under Dynamic Action Space}},
  year = {2026},
  url = {https://openreview.net/forum?id=R8Vh0HzCDs},
  howpublished = {OpenReview},
  note = {Submitted to ICLR 2026},
}
Figure