Learning to Adapt: Representation-Based Reinforcement Learning for Multi-Task Skill Transfer

• URL: http://arxiv.org/abs/2606.12890v1
• Date: Thu, 11 Jun 2026 04:33:03 GMT
• Title: Learning to Adapt: Representation-Based Reinforcement Learning for Multi-Task Skill Transfer
• Abstract summary: RepMT-SAC is a framework for multi-task RL that enables efficient knowledge sharing and robust transfer to new tasks.<n>We evaluate RepMT-SAC on trajectory-following tasks across in-distribution and out-of-distribution contexts, demonstrating that it outperforms baselines by up to 30%.
• Score: 5.787601808065202
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement learning has achieved remarkable success in learning complex control policies, yet its applicability remains limited due to sample inefficiency and poor generalization across tasks. In this work, we propose RepMT-SAC, a framework for multi-task RL that enables efficient knowledge sharing and robust transfer to new tasks. RepMT-SAC uses spectral MDP decomposition to capture transferable dynamics, structuring the value function into a task-agnostic core with a minimal task-specific adjustment. This design allows for strong zero-shot performance on in-distribution tasks and rapid few-shot adaptation to out-of-distribution tasks. We evaluate RepMT-SAC on quadcopter trajectory-following tasks across in-distribution and out-of-distribution contexts, demonstrating that it outperforms baselines by up to 30%.

Related papers

• Reward-Conditioned Reinforcement Learning [56.417273471201845]
  We introduce Reward-Conditioned Reinforcement Learning (RCRL), a framework that trains a single agent to optimize a family of reward specifications.<n>RCRL conditions the agent on reward parameterizations and learns multiple reward objectives from a shared replay data entirely off-policy.<n>Our results demonstrate that RCRL provides a scalable mechanism for learning robust, steerable policies without sacrificing the simplicity of single-task training.
  arXiv  Detail & Related papers  (2026-03-05T11:29:17Z)
• Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners [60.75160178669076]
  We show that the use of high-capacity value models trained via cross-entropy and conditioned on learnable task embeddings addresses the problem of task interference in online reinforcement learning.<n>We test our approach on 7 multi-task benchmarks with over 280 unique tasks, spanning high degree-of-freedom humanoid control and discrete vision-based RL.
  arXiv  Detail & Related papers  (2025-05-29T06:41:45Z)
• ThanoRA: Task Heterogeneity-Aware Multi-Task Low-Rank Adaptation [96.86211867758652]
  Low-Rank Adaptation (LoRA) is widely adopted for downstream fine-tuning of foundation models.<n>We propose ThanoRA, a Task Heterogeneity-Aware Multi-Task Low-Rank Adaptation framework.
  arXiv  Detail & Related papers  (2025-05-24T11:01:45Z)
• Efficient Knowledge Transfer in Multi-Task Learning through Task-Adaptive Low-Rank Representation [11.955971931186006]
  Pre-trained language models struggle with emerging tasks unseen during training in real-world applications.<n>We propose Task-Adaptive Low-Rank Representation (TA-LoRA), an MTL method built on prompt tuning.<n>Experiments on 16 tasks demonstrate that TA-LoRA achieves state-of-the-art performance in full-data and few-shot settings.
  arXiv  Detail & Related papers  (2025-04-20T06:33:19Z)
• Multi-Task Reinforcement Learning for Quadrotors [18.71563817810032]
  This paper presents a novel multi-task reinforcement learning (MTRL) framework tailored for quadrotor control.<n>By employing a multi-critic architecture and shared task encoders, our framework facilitates knowledge transfer across tasks, enabling a single policy to execute diverse maneuvers.
  arXiv  Detail & Related papers  (2024-12-17T01:10:18Z)
• Centralized Reward Agent for Knowledge Sharing and Transfer in Multi-Task Reinforcement Learning [13.25661582723752]
  We propose a novel multi-task reinforcement learning framework that integrates a central reward agent (CRA) and multiple distributed policy agents.<n>CRA functions as a knowledge pool, aimed at distilling knowledge from various tasks and distributing it to individual policy agents to improve learning efficiency.<n>We validate the proposed method on both discrete and continuous domains, including the representative Meta-World benchmark.
  arXiv  Detail & Related papers  (2024-08-20T13:49:26Z)
• Re-TASK: Revisiting LLM Tasks from Capability, Skill, and Knowledge Perspectives [54.14429346914995]
  Chain-of-Thought (CoT) has become a pivotal method for solving complex problems with large language models (LLMs)<n>This paper introduces the Re-TASK framework, a novel theoretical model that revisits LLM tasks from capability, skill, and knowledge perspectives.<n> Experiments across diverse domains demonstrate the effectiveness of Re-TASK.
  arXiv  Detail & Related papers  (2024-08-13T13:58:23Z)
• Efficient Multi-Task Reinforcement Learning via Task-Specific Action Correction [10.388605128396678]
  Task-Specific Action Correction is designed for simultaneous learning of multiple tasks. ACP incorporates goal-oriented sparse rewards, enabling an agent to adopt a long-term perspective. Additional rewards transform the original problem into a multi-objective MTRL problem.
  arXiv  Detail & Related papers  (2024-04-09T02:11:35Z)
• Meta-Reinforcement Learning Based on Self-Supervised Task Representation Learning [23.45043290237396]
  MoSS is a context-based Meta-reinforcement learning algorithm based on Self-Supervised task representation learning. On MuJoCo and Meta-World benchmarks, MoSS outperforms prior in terms of performance, sample efficiency (3-50x faster), adaptation efficiency, and generalization.
  arXiv  Detail & Related papers  (2023-04-29T15:46:19Z)
• Learning Action Translator for Meta Reinforcement Learning on Sparse-Reward Tasks [56.63855534940827]
  This work introduces a novel objective function to learn an action translator among training tasks. We theoretically verify that the value of the transferred policy with the action translator can be close to the value of the source policy. We propose to combine the action translator with context-based meta-RL algorithms for better data collection and more efficient exploration during meta-training.
  arXiv  Detail & Related papers  (2022-07-19T04:58:06Z)
• Task Adaptive Parameter Sharing for Multi-Task Learning [114.80350786535952]
  Adaptive Task Adapting Sharing (TAPS) is a method for tuning a base model to a new task by adaptively modifying a small, task-specific subset of layers. Compared to other methods, TAPS retains high accuracy on downstream tasks while introducing few task-specific parameters. We evaluate our method on a suite of fine-tuning tasks and architectures (ResNet, DenseNet, ViT) and show that it achieves state-of-the-art performance while being simple to implement.
  arXiv  Detail & Related papers  (2022-03-30T23:16:07Z)

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.