paper-with-me

Papers

Test-Time Regret Minimization in Meta Reinforcement Learning

2024-06-04 · Mirco Mutti, Aviv Tamar

Meta reinforcement learning sets a distribution over a set of tasks on which the agent can train at will, then is asked to learn an optimal policy for any test task efficiently. In this paper, we consider a finite set of tasks modeled through Markov decision processes with various dynamics. We assume to have endured a long training phase, from which the set of tasks is perfectly recovered, and we focus on regret minimization against the optimal policy in the unknown test task. Under a separation condition that states the existence of a state-action pair revealing a task against another, Chen et al. (2022) show that $O(M^2 \log(H))$ regret can be achieved, where $M, H$ are the number of tasks in the set and test episodes, respectively. In our first contribution, we demonstrate that the latter rate is nearly optimal by developing a novel lower bound for test-time regret minimization under separation, showing that a linear dependence with $M$ is unavoidable. Then, we present a family of stronger yet reasonable assumptions beyond separation, which we call strong identifiability, enabling algorithms achieving fast rates $\log (H)$ and sublinear dependence with $M$ simultaneously. Our paper provides a new understanding of the statistical barriers of test-time regret minimization and when fast rates can be achieved.

📄 PDF Abstract BibTeX arXiv:2406.02282

Code (0)

등록된 구현이 없습니다.

Tasks

Meta Reinforcement Learningreinforcement-learningReinforcement Learning

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Focus 설명 없음

Similar Papers 제목 키워드 기반

Meta-Learning for Simple Regret Minimization

2022-02-25 · MohammadJavad Azizi, Branislav Kveton, Mohammad Ghavamzadeh, Sumeet Katariya

We develop a meta-learning framework for simple regret minimization in bandits. In this framework, a learning agent interacts with a sequence of bandit tasks, which are sampled i.i.d.\ from an unknown prior distribution,…

Meta-Learning

Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning

2025-03-10 · Yuxiao Qu, Matthew Y. R. Yang, Amrith Setlur, Lewis Tunstall 외

Training models to effectively use test-time compute is crucial for improving the reasoning performance of LLMs. Current methods mostly do so via fine-tuning on search traces or running RL with 0/1 outcome reward, but do…

MathMeta Reinforcement LearningReinforcement Learning (RL)

Meta-Learning in Self-Play Regret Minimization

2025-04-26 · David Sychrovský, Martin Schmid, Michal Šustr, Michael Bowling

Regret minimization is a general approach to online optimization which plays a crucial role in many algorithms for approximating Nash equilibria in two-player zero-sum games. The literature mainly focuses on solving indi…

Meta-Learning

Regret Minimization Experience Replay in Off-Policy Reinforcement Learning

2021-05-15 · NeurIPS 2021 12 · Xu-Hui Liu, Zhenghai Xue, Jing-Cheng Pang, Shengyi Jiang 외

In reinforcement learning, experience replay stores past samples for further reuse. Prioritized sampling is a promising technique to better utilize these samples. Previous criteria of prioritization include TD error, rec…

MuJoCoreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Approximating Nash Equilibria in General-Sum Games via Meta-Learning

2025-04-26 · David Sychrovský, Christopher Solinas, Revan MacQueen, Kevin Wang 외

Nash equilibrium is perhaps the best-known solution concept in game theory. Such a solution assigns a strategy to each player which offers no incentive to unilaterally deviate. While a Nash equilibrium is guaranteed to a…

Meta-Learning