Test-Time Regret Minimization in Meta Reinforcement Learning

• URL: http://arxiv.org/abs/2406.02282v1
• Date: Tue, 4 Jun 2024 12:56:10 GMT
• Title: Test-Time Regret Minimization in Meta Reinforcement Learning
• Abstract summary: We consider a finite set of tasks modeled through Markov decision processes with various dynamics. We focus on regret minimization against the optimal policy in the unknown test task.
• Score: 28.710895687701353
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Contaminated Multi-task Learning with Heterogeneity: Fundamental Limits and Optimal Algorithms [5.54992643082602]
  We study a contaminated multi-task empirical risk minimization framework.<n>Our goal is to estimate both the global minimizer of the average risk and the clean task-specific minimizers.<n>We propose a computationally efficient filtering-based robust multi-task gradient descent method.
  arXiv  Detail & Related papers  (2026-07-02T18:23:41Z)
• Provably Efficient and Agile Randomized Q-Learning [35.14581235983678]
  We propose a novel variant of Q-learning algorithm, refereed to as RandomizedQ, which integrates sampling-based exploration with agile, step-wise, policy updates.<n> Empirically, RandomizedQ exhibits outstanding performance compared to existing Q-learning variants with both bonus-based and Bayesian-based exploration on standard benchmarks.
  arXiv  Detail & Related papers  (2025-06-30T16:08:29Z)
• From Continual Learning to SGD and Back: Better Rates for Continual Linear Models [50.11453013647086]
  We analyze the forgetting, i.e., loss on previously seen tasks, after $k$ iterations.<n>We develop novel last-iterate upper bounds in the realizable least squares setup.<n>We prove for the first time that randomization alone, with no task repetition, can prevent catastrophic in sufficiently long task sequences.
  arXiv  Detail & Related papers  (2025-04-06T18:39:45Z)
• Rethinking Fine-Tuning when Scaling Test-Time Compute: Limiting Confidence Improves Mathematical Reasoning [32.45574194957491]
  We show that training with cross-entropy loss can be misaligned with pass@N in that pass@N accuracy $it decreases$ with longer training. We suggest a principled, modified training loss that is better aligned to pass@N by limiting model confidence and rescuing pass@N test performance.
  arXiv  Detail & Related papers  (2025-02-11T00:33:31Z)
• Settling Constant Regrets in Linear Markov Decision Processes [57.34287648914407]
  We study the constant regret guarantees in reinforcement learning (RL) We introduce an algorithm, Cert-LSVI-UCB, for misspecified linear Markov decision processes (MDPs) For an MDP characterized by a minimal suboptimality gap $Delta$, Cert-LSVI-UCB has a cumulative regret of $tildemathcalO(d3H5/Delta)$ with high probability, provided that the misspecification level $zeta$ is below $tildemathcalO(Delta / (sqrtd
  arXiv  Detail & Related papers  (2024-04-16T17:23:19Z)
• Settling the Sample Complexity of Online Reinforcement Learning [92.02082223856479]
  We show how to achieve minimax-optimal regret without incurring any burn-in cost.<n>We extend our theory to unveil the influences of problem-dependent quantities like the optimal value/cost and certain variances.
  arXiv  Detail & Related papers  (2023-07-25T15:42:11Z)
• Provably Efficient Lifelong Reinforcement Learning with Linear Function Approximation [41.460894569204065]
  We study lifelong reinforcement learning (RL) in a regret setting of linear contextual Markov decision process (MDP) We propose an algorithm, called UCB Lifelong Value Distillation (UCBlvd), that provably achieves sublinear regret for any sequence of tasks.
  arXiv  Detail & Related papers  (2022-06-01T06:53:28Z)
• Multi-task Representation Learning with Stochastic Linear Bandits [29.8208189270894]
  We study the problem of transfer-learning in the setting of linear bandit tasks. We consider that a low dimensional linear representation is shared across the tasks, and study the benefit of learning this representation in the multi-task learning setting.
  arXiv  Detail & Related papers  (2022-02-21T09:26:34Z)
• New Tight Relaxations of Rank Minimization for Multi-Task Learning [161.23314844751556]
  We propose two novel multi-task learning formulations based on two regularization terms. We show that our methods can correctly recover the low-rank structure shared across tasks, and outperform related multi-task learning methods.
  arXiv  Detail & Related papers  (2021-12-09T07:29:57Z)
• Breaking the Sample Complexity Barrier to Regret-Optimal Model-Free Reinforcement Learning [52.76230802067506]
  A novel model-free algorithm is proposed to minimize regret in episodic reinforcement learning. The proposed algorithm employs an em early-settled reference update rule, with the aid of two Q-learning sequences. The design principle of our early-settled variance reduction method might be of independent interest to other RL settings.
  arXiv  Detail & Related papers  (2021-10-09T21:13:48Z)
• Instance-optimality in optimal value estimation: Adaptivity via variance-reduced Q-learning [99.34907092347733]
  We analyze the problem of estimating optimal $Q$-value functions for a discounted Markov decision process with discrete states and actions. Using a local minimax framework, we show that this functional arises in lower bounds on the accuracy on any estimation procedure. In the other direction, we establish the sharpness of our lower bounds, up to factors logarithmic in the state and action spaces, by analyzing a variance-reduced version of $Q$-learning.
  arXiv  Detail & Related papers  (2021-06-28T00:38:54Z)
• Navigating to the Best Policy in Markov Decision Processes [68.8204255655161]
  We investigate the active pure exploration problem in Markov Decision Processes. Agent sequentially selects actions and, from the resulting system trajectory, aims at the best as fast as possible.
  arXiv  Detail & Related papers  (2021-06-05T09:16:28Z)
• Optimal Algorithms for Stochastic Multi-Armed Bandits with Heavy Tailed Rewards [24.983866845065926]
  We consider multi-armed bandits with heavy-tailed rewards, whose $p$-th moment is bounded by a constant $nu_p$ for $1pleq2$. We propose a novel robust estimator which does not require $nu_p$ as prior information. We show that an error probability of the proposed estimator decays exponentially fast.
  arXiv  Detail & Related papers  (2020-10-24T10:44:02Z)
• Reparameterized Variational Divergence Minimization for Stable Imitation [57.06909373038396]
  We study the extent to which variations in the choice of probabilistic divergence may yield more performant ILO algorithms. We contribute a re parameterization trick for adversarial imitation learning to alleviate the challenges of the promising $f$-divergence minimization framework. Empirically, we demonstrate that our design choices allow for ILO algorithms that outperform baseline approaches and more closely match expert performance in low-dimensional continuous-control tasks.
  arXiv  Detail & Related papers  (2020-06-18T19:04:09Z)
• Upper Confidence Primal-Dual Reinforcement Learning for CMDP with Adversarial Loss [145.54544979467872]
  We consider online learning for episodically constrained Markov decision processes (CMDPs) We propose a new emphupper confidence primal-dual algorithm, which only requires the trajectories sampled from the transition model. Our analysis incorporates a new high-probability drift analysis of Lagrange multiplier processes into the celebrated regret analysis of upper confidence reinforcement learning.
  arXiv  Detail & Related papers  (2020-03-02T05:02:23Z)
• Task-Robust Model-Agnostic Meta-Learning [42.27488241647739]
  We introduce the notion of "task-robustness" by reformulating the popular ModelAgnostic Meta-Learning (AML) objective. The solution to this novel formulation is taskrobust in the sense that it places equal importance on even the most difficult/or rare tasks.
  arXiv  Detail & Related papers  (2020-02-12T02:20:51Z)

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.