Hybrid RL algorithms improve offline and online RL in linear MDPs.
problem Improving RL performance without single-policy concentrability.
method Developed computationally efficient algorithms for PAC and regret-minimizing RL in linear MDPs.
result Achieved sharper error or regret bounds for linear MDPs.
Unified hybrid RL algorithm improves online RL performance with offline data.
problem Improving reinforcement learning performance with limited online data.
method A unified hybrid RL algorithm combining offline and online data.
result Unified algorithm achieves state-of-the-art results in sub-optimality gap and online learning regret.
FMDP-BF algorithm improves RL in factored MDPs with exponential regret reduction.
problem Efficient reinforcement learning in factored MDPs with constrained RL.
method FMDP-BF algorithm leveraging factorization structure of FMDPs.
result FMDP-BF's regret is exponentially smaller than optimal algorithms for non-factored MDPs.
New RL algorithm reduces regret in finite-horizon episodic tasks.
problem Minimizing regret in model-based reinforcement learning.
method Optimism principle applied to value-targeted regression.
result Regret bound of i l d e O ( d H 3 T ) ilde{\mathcal{O}}(d\sqrt{H^{3}T}) i l d e O ( d H 3 T ) for linear mixtures. We present a reduction from reinforcement learning (RL) to no-regret online learning based on the saddle-point formulation of RL, by which "any" online algorithm with sublinear regret can generate policies with provable performance guarantees. This new perspective decouples the RL problem into two parts: regret minimiz…
Improved privacy in RL with near-optimal regret bounds.
problem Privacy-preserving reinforcement learning in personalized decision-making systems.
method Differentially private algorithm based on LSVI-UCB++ with privacy-preserving techniques.
result Achieved a near-optimal regret bound of O(d * sqrt(H^3 * K) + H^(15/4) * d^(7/6) * K^(1/2) / ε).
New RL algorithms reduce costs for single-agent and federated learning.
problem Minimizing costs in RL and federated RL settings.
method Q-EarlySettled-LowCost and FedQ-EarlySettled-LowCost algorithms.
result First algorithms to achieve low burn-in and logarithmic switching costs.
Quantum RL algorithm achieves logarithmic regret for exploration.
problem Designing efficient quantum RL algorithms for exploration.
method UCRL-style quantum algorithm with lazy updating and quantum estimation.
result Proves O ( p o l y ( S , A , H , log T ) ) \mathcal{O}(\mathrm{poly}(S, A, H, \log T)) O ( poly ( S , A , H , log T )) worst-case regret. A new batch ensemble method reduces regret in stochastic bandits.
problem Efficiently balancing exploration and exploitation in online RL.
method Proposes a batch ensemble scheme to achieve near-optimal regret.
result Proves near-optimal regret with a single parameter independent of variance.
New RL algorithm reduces deployment cost for linear function approximations.
problem Efficiently deploying new policies in RL with unknown rewards.
method Proposes an algorithm that minimizes trajectories needed for identifying optimal policies.
result Achieves optimal deployment complexity and sample complexity.
New RL algorithm achieves nearly optimal performance for linear MDPs.
problem Optimal reinforcement learning for episodic linear MDPs.
method Weighted linear regression with variance estimator and rare-switching policy.
result Achieves nearly minimax optimal regret i l d e O ( d H 3 K ) ilde O(d\sqrt{H^3K}) i l d e O ( d H 3 K ) . Optimization of parameterized policies for reinforcement learning (RL) is an important and challenging problem in artificial intelligence. Among the most common approaches are algorithms based on gradient ascent of a score function representing discounted return. In this paper, we examine the role of these policy gradi…
New RL algorithms use lookahead info to maximize rewards.
problem RL in unknown environments without lookahead info.
method Planning using empirical reward and transition distributions.
result Achieves tight regret compared to lookahead info.
New spectral methods improve matrix estimation in RL with low-rank structure.
problem Estimating matrices with low-rank structure in reinforcement learning.
method Spectral-based matrix estimation approaches.
result Spectral methods efficiently recover singular subspaces and minimize entry-wise error.
New algorithm reduces switching costs in RL beyond linear MDPs.
problem Costly policy switching in reinforcement learning.
method ELEANOR-LowSwitching algorithm for linear Bellman-complete MDPs.
result Achieves near-optimal regret with logarithmic switching cost.
Regret minimization is a powerful tool for solving large-scale problems; it was recently used in breakthrough results for large-scale extensive-form game solving. This was achieved by composing simplex regret minimizers into an overall regret-minimization framework for extensive-form game strategy spaces. In this paper…
Proposes a new theoretical framework for PbRL that requires less human feedback.
problem Lack of theoretical work capturing practical PbRL frameworks.
method Introduces a reward-agnostic PbRL framework that acquires exploratory trajectories before human feedback.
result Demonstrates improved sample complexity for learning optimal policies in linear and low-rank MDPs.
New RL algorithm reduces sample complexity for optimal learning.
problem Achieving optimal learning with minimal samples in RL.
method Early-settled variance reduction method with Q-learning sequences.
result Near-optimal regret achieved with sample size S A p o l y ( H ) SA\,\mathrm{poly}(H) S A poly ( H ) . Efficient RL for linear MDPs with unknown transitions.
problem Long planning horizons and unknown state transitions in linear mixture MDPs.
method Horizon-free algorithm using weighted least squares with variance and uncertainty awareness.
result Achieves optimal regret up to logarithmic factors.
New algorithm reduces regret in stochastic shortest path problems.
problem Planning and control in environments with unknown dynamics and variable episode lengths.
method Developed an algorithm with a new regret bound of O ( B ⋆ ∣ S ∣ ∣ A ∣ K ) O(B_\star |S| \sqrt{|A| K}) O ( B ⋆ ∣ S ∣ ∣ A ∣ K ) . result Guaranteed a significant reduction in regret compared to previous methods.
Paper tackles robust knowledge transfer in parallel RL tasks.
problem Transfer knowledge from low-tier to high-tier tasks in parallel RL without shared dynamics or reward functions.
method Identifies Optimal Value Dominance condition and proposes online learning algorithms for both tasks.
result Achieves constant regret on partial states and near-optimal regret when tasks are dissimilar.
Paper eliminates warm-up phase for PO in linear MDPs, achieving optimal regret.
problem Costly warm-up phase in PO algorithms for linear MDPs.
method Simple contraction mechanism replaces warm-up phase.
result Achieves rate-optimal regret with improved dependence on problem parameters.
Attackers can poison environments to force RL agents to follow target policies.
problem Security threat to reinforcement learning where attackers manipulate environments to force agents into following target policies.
method Optimization framework for finding optimal stealthy attacks under different measures of attack cost.
result Attackers can easily succeed in teaching any target policy to RL agents under mild conditions.
Algorithm POLO learns low-rank MDPs with adversarial changes in full-info feedback.
problem Learning low-rank MDPs with adversarial changes and unknown transition probabilities.
method Policy optimization-based algorithm POLO with regret guarantee.
result POLO achieves sublinear regret guarantee with no dependence on state space size.
New algorithm selects optimal subset for multiclass classifier training.
problem Selecting optimal subset of labeled examples for multiclass classifier training.
method Regret minimization framework with new regularization scheme.
result New method consistently outperforms state-of-the-art approaches.
Algorithm minimizes regret and converges to equilibria in Markov games.
problem Regret minimization and convergence to equilibria in general-sum Markov games under adversarial opponents.
method Decentralized algorithm that uses policy optimization and controls path length to achieve sublinear regret.
result Sublinear regret guarantees for convergence to correlated equilibrium in Markov games.
Paper explores rate-preserving reductions between Blackwell approachability and no-regret learning.
problem Tackles rate-preserving reductions between Blackwell approachability and no-regret learning.
method Studies fine-grained reductions and optimal rates of convergence.
result Shows that rate-preserving reductions do not always hold, but provides conditions for when they do.
Dynamic regret minimization is shown equivalent to static regret minimization for linear losses.
problem Dynamic regret minimization in online convex optimization.
method Equivalence between dynamic and static regret minimization for linear losses.
result Dynamic regret minimization is equivalent to static regret minimization for linear losses.
This paper begins with a study on the dual representations of risk and regret measures and their impact on modeling multistage decision making under uncertainty. A relationship between risk envelopes and regret envelopes is established by using the Lagrangian duality theory. Such a relationship opens a door to a decomp…
Improved MORE algorithm reduces regret in black-box optimization and RL tasks.
problem Noisy fitness evaluations and poor sample quality in black-box optimization.
method Decouples mean and covariance updates, uses entropy scheduling, and simplifies model learning.
result Significantly reduces regret in black-box optimization and RL tasks.
Survey of universal portfolio techniques for minimizing investment regret.
problem Minimizing investment regret in algorithmic trading.
method Explains various universal portfolio techniques and their proofs.
result Coverage of fundamental concepts and algorithms in regret minimization.
We present an algorithm based on the \emph{Optimism in the Face of Uncertainty} (OFU) principle which is able to learn Reinforcement Learning (RL) modeled by Markov decision process (MDP) with finite state-action space efficiently. By evaluating the state-pair difference of the optimal bias function h ∗ h^{*} h ∗ , the propos…
There are two variants of the classical multi-armed bandit (MAB) problem that have received considerable attention from machine learning researchers in recent years: contextual bandits and simple regret minimization. Contextual bandits are a sub-class of MABs where, at every time step, the learner has access to side in…
We consider regret minimization in repeated games with non-convex loss functions. Minimizing the standard notion of regret is computationally intractable. Thus, we define a natural notion of regret which permits efficient optimization and generalizes offline guarantees for convergence to an approximate local optimum. W…
Optimal algorithm for minimizing regret in heavy-tailed bandits.
problem Minimizing regret in stochastic multi-armed bandits with heavy-tailed distributions.
method Proposes an optimal algorithm under the assumption of uniformly bounded moments of order (1+ε).
result Matches the lower bound exactly in the first-order term and provides a finite-time bound on its regret.
The CFR framework has been a powerful tool for solving large-scale extensive-form games in practice. However, the theoretical rate at which past CFR-based algorithms converge to the Nash equilibrium is on the order of O ( T − 1 / 2 ) O(T^{-1/2}) O ( T − 1/2 ) , where T T T is the number of iterations. In contrast, first-order methods can be used to …
Quantum UCB algorithm reduces reinforcement learning regret exponentially.
problem Episodic reinforcement learning with quantum state evolution.
method Upper Confidence Bound (UCB) quantum algorithm with quantum mean estimation.
result Exponential improvement in regret from $\Tilde{\mathcal{O}}(\sqrt{K})$ to $\Tilde{\mathcal{O}}(1)$ .
Paper addresses regret minimization and inference in high-dimensional online decision-making.
problem Regret minimization and statistical inference in high-dimensional online decision-making.
method Integrates ε-greedy bandit algorithm with hard thresholding for sparse bandit parameters and debiasing method for inference.
result Achieves either O ( T 1 / 2 ) O(T^{1/2}) O ( T 1/2 ) regret or O ( T 1 / 2 ) O(T^{1/2}) O ( T 1/2 ) -consistent inference, with trade-off between exploration and exploitation. Paper tackles hidden game problem in AI alignment and language games.
problem Hidden game problem in AI alignment and language games.
method Developed a composition of regret minimization techniques to discover and exploit hidden structures.
result Achieved optimal external and swap regret bounds for rapid convergence to correlated equilibria.
New algorithms minimize simple and cumulative regret in contextual bandits.
problem Minimizing simple and cumulative regret in contextual bandit settings.
method Proposed new algorithms using conformal arm sets (CASs).
result Near-optimal minimax guarantees for simple regret and state-of-the-art guarantees for cumulative regret.
The paper minimizes Borda regret in dueling bandits models.
problem Minimizing Borda regret in dueling bandits models.
method Proposes explore-then-commit and EXP3-type algorithms for stochastic and adversarial settings respectively.
result Achieves nearly matching regret upper bounds of O ( d 2 / 3 T 2 / 3 ) O(d^{2/3} T^{2/3}) O ( d 2/3 T 2/3 ) for both settings. New algorithm reduces regret by allowing free exploration in multi-armed bandits.
problem Designing an adaptive policy to minimize regret with a free exploration budget.
method Introduced ( α , β ) (α,β) ( α , β ) -probably saving policies and a two-phase algorithm UFE-KLUCB-H. result UFE-KLUCB-H accumulates strictly less regret than non-free exploration policies.
Efficient boosting method for regression with limited feedback.
problem Online boosting for regression tasks with noisy multi-point bandit feedback.
method Efficient regret minimization method with online boosting algorithm and projection-free online convex optimization.
result Improved state-of-the-art guarantees in efficiency.
Unified framework for best arm identification and dueling bandits regret minimization.
problem Best arm identification and dueling bandits regret minimization.
method Tree-Guided Identify-Then-Exploit (TG-ITE) framework.
result Unified approach achieving optimal sample complexity and regret guarantees.
We consider online algorithms under both the competitive ratio criteria and the regret minimization one. Our main goal is to build a unified methodology that would be able to guarantee both criteria simultaneously. For a general class of online algorithms, namely any Metrical Task System (MTS), we show that one can sim…
Algorithm minimizes regret in multi-criteria bandits with constraints.
problem Optimize primary attribute while respecting secondary constraints.
method Con-LCB algorithm that guarantees logarithmic regret and feasibility identification.
result Logarithmic regret and feasibility identification with high probability.
The paper improves on existing algorithms for minimizing different types of regret in online learning.
problem Minimizing external, internal, and swap regret in online learning with multiple experts.
method Develops a single algorithm using φ-regret minimization and Haar-wavelet-inspired matrix features to achieve optimal bounds in various scenarios.
result Achieves optimal bounds for external, internal, and swap regrets in different expert scenarios.
ALMAB-DC optimizes expensive black-box experiments using active learning and distributed computing.
problem Efficiently optimizing expensive, gradient-free objectives in computational statistics and machine learning.
method Combines active learning, multi-armed bandits, and distributed asynchronous computing.
result Achieves lower simple regret and superior performance in various tasks compared to non-ALMAB baselines.