# Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning

arXiv: https://arxiv.org/abs/2502.02332 · HTML: https://mlsanity.com/paper/2502.02332/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 36 of its 53 references that are in the map.
- First posted on arXiv 4 Feb 2025.

## Placed in

- Deep reinforcement learning methods / [Deep RL algorithms and representations](https://mlsanity.com/deeprl/deep-rl-algorithms-and-representations/)

## Builds on (most cited first, 30 of 36)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [On the Convergence of FedAvg on Non-IID Data](https://mlsanity.com/paper/1907.02189/) (2019)
- [Local SGD Converges Fast and Communicates Little](https://mlsanity.com/paper/1805.09767/) (2018)
- [Evolution Strategies as a Scalable Alternative to Reinforcement Learning](https://mlsanity.com/paper/1703.03864/) (2017)
- [RL2: Fast Reinforcement Learning via Slow Reinforcement Learning](https://mlsanity.com/paper/1611.02779/) (2016)
- [Learning to reinforcement learn](https://mlsanity.com/paper/1611.05763/) (2016)
- [Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning](https://mlsanity.com/paper/1803.11347/) (2018)
- [GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Training](https://mlsanity.com/paper/2103.00123/) (2021)
- [Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator](https://mlsanity.com/paper/1801.05039/) (2018)
- [Loss landscapes and optimization in over-parameterized non-linear systems and neural networks](https://mlsanity.com/paper/2003.00307/) (2020)
- [Preparing for the Unknown: Learning a Universal Policy with Online System Identification](https://mlsanity.com/paper/1702.02453/) (2017)
- [GCR: Gradient Coreset Based Replay Buffer Selection For Continual Learning](https://mlsanity.com/paper/2111.11210/) (2021)
- [ProMP: Proximal Meta-Policy Search](https://mlsanity.com/paper/1810.06784/) (2018)
- [Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?](https://mlsanity.com/paper/1812.10004/) (2018)
- [Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems](https://mlsanity.com/paper/1812.08305/) (2018)
- [Adaptive Second Order Coresets for Data-efficient Machine Learning](https://mlsanity.com/paper/2207.13887/) (2022)
- [ES-MAML: Simple Hessian-Free Meta Learning](https://mlsanity.com/paper/1910.01215/) (2019)
- [Meta Reinforcement Learning for Sim-to-real Domain Adaptation](https://mlsanity.com/paper/1909.12906/) (2019)
- [Learning Fast Adaptation with Meta Strategy Optimization](https://mlsanity.com/paper/1909.12995/) (2019)
- [Towards Sustainable Learning: Coresets for Data-efficient Deep Learning](https://mlsanity.com/paper/2306.01244/) (2023)
- [Rapidly Adaptable Legged Robots via Evolutionary Meta-Learning](https://mlsanity.com/paper/2003.01239/) (2020)
- [Multi-Task Imitation Learning for Linear Dynamical Systems](https://mlsanity.com/paper/2212.00186/) (2022)
- [Model-free Learning with Heterogeneous Dynamical Systems: A Federated LQR Approach](https://mlsanity.com/paper/2308.11743/) (2023)
- [Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platforms](https://mlsanity.com/paper/2103.03697/) (2021)
- [Meta-Learning Linear Quadratic Regulators: A Policy Gradient MAML Approach for Model-free LQR](https://mlsanity.com/paper/2401.14534/) (2024)
- [Learning Personalized Models with Clustered System Identification](https://mlsanity.com/paper/2304.01395/) (2023)
- [Information-theoretic Task Selection for Meta-Reinforcement Learning](https://mlsanity.com/paper/2011.01054/) (2020)
- [Zeroth-Order Feedback Optimization for Cooperative Multi-Agent Systems](https://mlsanity.com/paper/2011.09728/) (2020)
- [Nonasymptotic Regret Analysis of Adaptive Linear Quadratic Control with Model Misspecification](https://mlsanity.com/paper/2401.00073/) (2023)
- [Convergence of Gradient-based MAML in LQR](https://mlsanity.com/paper/2309.06588/) (2023)

## Built on by (most cited first, 6 of 6)

- [A Coreset Selection of Coreset Selection Literature: Introduction and Recent Advances](https://mlsanity.com/paper/2505.17799/) (2025)
- [Collaborative Bayesian Optimization via Wasserstein Barycenters](https://mlsanity.com/paper/2504.10770/) (2025)
- [The Role of Diversity in In-Context Learning for Large Language Models](https://mlsanity.com/paper/2505.19426/) (2025)
- [Learning Stabilizing Policies via an Unstable Subspace Representation](https://mlsanity.com/paper/2505.01348/) (2025)
- [Multitask LQG Control: Performance and Generalization Bounds](https://mlsanity.com/paper/2604.16730/) (2026)
- [Demystifying Manifold Constraints in LLM Pre-training](https://mlsanity.com/paper/2605.04418/) (2026)

## Abstract (arXiv)

We study task selection to enhance sample efficiency in model-agnostic meta-reinforcement learning (MAML-RL). Traditional meta-RL typically assumes that all available tasks are equally important, which can lead to task redundancy when they share significant similarities. To address this, we propose a coreset-based task selection approach that selects a weighted subset of tasks based on how diverse they are in gradient space, prioritizing the most informative and diverse tasks. Such task selection reduces the number of samples needed to find an ε-close stationary solution by a factor of O(1/ε). Consequently, it guarantees a faster adaptation to unseen tasks while focusing training on the most relevant tasks. As a case study, we incorporate task selection to MAML-LQR (Toso et al., 2024b), and prove a sample complexity reduction proportional to O(log(1/ε)) when the task specific cost also satisfy gradient dominance. Our theoretical guarantees underscore task selection as a key component for scalable and sample-efficient meta-RL. We numerically validate this trend across multiple RL benchmark problems, illustrating the benefits of task selection beyond the LQR baseline.