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

arXiv: https://arxiv.org/abs/2606.12890 · HTML: https://mlsanity.com/paper/2606.12890/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in RL for robot navigation and UAV control, one of 15 directions in Deep reinforcement learning methods.
- Builds on 14 of its 17 references that are in the map.
- First posted on arXiv 11 Jun 2026.

## Placed in

- Deep reinforcement learning methods / [RL for robot navigation and UAV control](https://mlsanity.com/deeprl/rl-for-robot-navigation-and-uav-control/)

## Builds on (most cited first, 14 of 14)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Provably Efficient Reinforcement Learning with Linear Function Approximation](https://mlsanity.com/paper/1907.05388/) (2019)
- [Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables](https://mlsanity.com/paper/1903.08254/) (2019)
- [Successor Features for Transfer in Reinforcement Learning](https://mlsanity.com/paper/1606.05312/) (2016)
- [VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning](https://mlsanity.com/paper/1910.08348/) (2019)
- [Reinforcement Learning in Feature Space: Matrix Bandit, Kernels, and Regret Bound](https://mlsanity.com/paper/1905.10389/) (2019)
- [Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes](https://mlsanity.com/paper/2408.03539/) (2024)
- [Representation Learning for Online and Offline RL in Low-rank MDPs](https://mlsanity.com/paper/2110.04652/) (2021)
- [An empirical investigation of the challenges of real-world reinforcement learning](https://mlsanity.com/paper/2003.11881/) (2020)
- [Making Linear MDPs Practical via Contrastive Representation Learning](https://mlsanity.com/paper/2207.07150/) (2022)
- [Spectral Decomposition Representation for Reinforcement Learning](https://mlsanity.com/paper/2208.09515/) (2022)
- [Latent Variable Representation for Reinforcement Learning](https://mlsanity.com/paper/2212.08765/) (2022)
- [Skill Transfer and Discovery for Sim-to-Real Learning: A Representation-Based Viewpoint](https://mlsanity.com/paper/2404.05051/) (2024)

## Built on by (most cited first, 1 of 1)

- [Teaching a Robot Dog New Tricks: Diverse Quadruped Skills via Combined Reinforcement and Imitation Learning with Adversarial Task Selection](https://mlsanity.com/paper/2610.10601/) (2026)

## Abstract (arXiv)

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%.