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

• URL: http://arxiv.org/abs/2506.05702v1
• Date: Fri, 06 Jun 2025 03:07:30 GMT
• Title: Action-Adaptive Continual Learning: Enabling Policy Generalization under Dynamic Action Spaces
• Authors: Chaofan Pan, Jiafen Liu, Yanhua Li, Linbo Xiong, Fan Min, Wei Wei, Xin Yang,
• Abstract summary: Continual Learning (CL) is a powerful tool that enables agents to learn a sequence of tasks.<n>Existing CL methods often assume that the agent's capabilities remain static within dynamic environments.<n>We propose an Action-Adaptive Continual Learning framework (AACL) to address this challenge.
• Score: 16.07372335607339
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Continual Learning (CL) is a powerful tool 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 Action-Adaptive Continual Learning 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.

Related papers

• Curriculum Learning With Counterfactual Group Relative Policy Advantage For Multi-Agent Reinforcement Learning [15.539607264374242]
  Multi-agent reinforcement learning (MARL) has achieved strong performance in cooperative adversarial tasks.<n>We propose a dynamic curriculum learning framework that employs an self-adaptive difficulty adjustment mechanism.<n>Our method improves both training stability and final performance, achieving competitive results against state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-06-09T08:38:18Z)
• Dynamic Manipulation of Deformable Objects in 3D: Simulation, Benchmark and Learning Strategy [88.8665000676562]
  Prior methods often simplify the problem to low-speed or 2D settings, limiting their applicability to real-world 3D tasks.<n>To mitigate data scarcity, we introduce a novel simulation framework and benchmark grounded in reduced-order dynamics.<n>We propose Dynamics Informed Diffusion Policy (DIDP), a framework that integrates imitation pretraining with physics-informed test-time adaptation.
  arXiv  Detail & Related papers  (2025-05-23T03:28:25Z)
• COMBO-Grasp: Learning Constraint-Based Manipulation for Bimanual Occluded Grasping [56.907940167333656]
  Occluded robot grasping is where the desired grasp poses are kinematically infeasible due to environmental constraints such as surface collisions.<n>Traditional robot manipulation approaches struggle with the complexity of non-prehensile or bimanual strategies commonly used by humans.<n>We introduce Constraint-based Manipulation for Bimanual Occluded Grasping (COMBO-Grasp), a learning-based approach which leverages two coordinated policies.
  arXiv  Detail & Related papers  (2025-02-12T01:31:01Z)
• Continual Task Learning through Adaptive Policy Self-Composition [54.95680427960524]
  CompoFormer is a structure-based continual transformer model that adaptively composes previous policies via a meta-policy network. Our experiments reveal that CompoFormer outperforms conventional continual learning (CL) methods, particularly in longer task sequences.
  arXiv  Detail & Related papers  (2024-11-18T08:20:21Z)
• DynaSaur: Large Language Agents Beyond Predefined Actions [108.75187263724838]
  Existing LLM agent systems typically select actions from a fixed and predefined set at every step.<n>We propose an LLM agent framework that can dynamically create and compose actions as needed.<n>In this framework, the agent interacts with its environment by generating and executing programs written in a general-purpose programming language.
  arXiv  Detail & Related papers  (2024-11-04T02:08:59Z)
• HAZARD Challenge: Embodied Decision Making in Dynamically Changing Environments [93.94020724735199]
  HAZARD consists of three unexpected disaster scenarios, including fire, flood, and wind. This benchmark enables us to evaluate autonomous agents' decision-making capabilities across various pipelines.
  arXiv  Detail & Related papers  (2024-01-23T18:59:43Z)
• Action Pick-up in Dynamic Action Space Reinforcement Learning [6.15205100319133]
  We propose an intelligent Action Pick-up (AP) algorithm to autonomously choose valuable actions that are most likely to boost performance from a set of new actions. In this paper, we first theoretically analyze and find that a prior optimal policy plays an important role in action pick-up by providing useful knowledge and experience. We then design two different AP methods: frequency-based global method and state clustering-based local method, based on the prior optimal policy.
  arXiv  Detail & Related papers  (2023-04-03T10:55:16Z)
• Learning Routines for Effective Off-Policy Reinforcement Learning [0.0]
  We propose a novel framework for reinforcement learning that effectively lifts such constraints. Within our framework, agents learn effective behavior over a routine space. We show that the resulting agents obtain relevant performance improvements while requiring fewer interactions with the environment per episode.
  arXiv  Detail & Related papers  (2021-06-05T18:41:57Z)
• PLAS: Latent Action Space for Offline Reinforcement Learning [18.63424441772675]
  The goal of offline reinforcement learning is to learn a policy from a fixed dataset, without further interactions with the environment. Existing off-policy algorithms have limited performance on static datasets due to extrapolation errors from out-of-distribution actions. We demonstrate that our method provides competitive performance consistently across various continuous control tasks and different types of datasets.
  arXiv  Detail & Related papers  (2020-11-14T03:38:38Z)
• ADAIL: Adaptive Adversarial Imitation Learning [11.270858993502705]
  We present the ADaptive Adversarial Imitation Learning (ADAIL) algorithm for learning adaptive policies that can be transferred between environments of varying dynamics. This is an important problem in robotic learning because in real world scenarios 1) reward functions are hard to obtain, 2) learned policies from one domain are difficult to deploy in another due to varying source to target domain statistics, and 3) collecting expert demonstrations in multiple environments where the dynamics are known and controlled is often infeasible.
  arXiv  Detail & Related papers  (2020-08-23T06:11:00Z)
• Discrete Action On-Policy Learning with Action-Value Critic [72.20609919995086]
  Reinforcement learning (RL) in discrete action space is ubiquitous in real-world applications, but its complexity grows exponentially with the action-space dimension. We construct a critic to estimate action-value functions, apply it on correlated actions, and combine these critic estimated action values to control the variance of gradient estimation. These efforts result in a new discrete action on-policy RL algorithm that empirically outperforms related on-policy algorithms relying on variance control techniques.
  arXiv  Detail & Related papers  (2020-02-10T04:23:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.