DDO-RM improves reward-based policies by converting reward scores into a target distribution.
problem Improving reward-based policies when the reward function is simpler than the policy.
method Converts reward scores into a target distribution and uses KL-regularized mirror-descent updates.
result DDO-RM outperforms DPO in pair accuracy and mean margin.
Paper generalizes reward distribution in multi-armed bandits with temporally-partitioned rewards.
problem Handling partial rewards distributed over multiple rounds in multi-armed bandits.
method Introduces Beta-spread property to generalize reward distribution, derives lower bound, and provides TP-UCB-FR-G algorithm.
result Improves regret upper bound for some scenarios using Beta-spread property.
We propose a generic, Bayesian, information geometric approach to the exploration--exploitation trade-off in multi-armed bandit problems. Our approach, BelMan, uniformly supports pure exploration, exploration--exploitation, and two-phase bandit problems. The knowledge on bandit arms and their reward distributions is su…
Reward collapse occurs when ranking-based reward models yield uniform rewards for different prompts.
problem Reward collapse in aligning large language models with human preferences.
method Introduced a prompt-aware optimization scheme to derive closed-form expressions for reward distributions.
result Our prompt-aware utility functions significantly alleviate reward collapse during training.
Iterative tilting fine-tunes diffusion models for reward-tilted distributions.
problem Fine-tuning diffusion models for reward-tilted distributions.
method Decomposes large reward tilts into smaller, tractable tilts via first-order Taylor expansion, avoiding backpropagation.
result Validated on a two-dimensional Gaussian mixture, achieving exact closed-form solutions.
We here adopt Bayesian nonparametric mixture models to extend multi-armed bandits in general, and Thompson sampling in particular, to scenarios where there is reward model uncertainty. In the stochastic multi-armed bandit, the reward for the played arm is generated from an unknown distribution. Reward uncertainty, i.e.…
The paper proves the convergence of Q-value for Gaussian rewards.
problem Existing proofs cannot guarantee convergence of the Q-function for Gaussian rewards.
method Using the central limit theorem and relaxing the condition to E[r(s,a)2]<∞. result Proves the convergence of the Q-function under the condition of E[r(s,a)2]<∞. Learning reward functions can lead to poor policy performance despite low error.
problem Low error in learned reward functions does not guarantee low regret in policy performance.
method Mathematical analysis of reward learning and policy optimization.
result A low expected test error of the reward model guarantees low worst-case regret, but error-regret mismatch can occur with certain data distributions.
New algorithm reduces worst-case regret for heavy-tailed bandits.
problem Stochastic Multi-Armed Bandit problem with heavy-tailed rewards.
method Modified minimax policy MOSS with saturated empirical mean.
result Worst-case regret matching lower bound for heavy-tailed distributions.
New algorithms for multivariate RL improve decision-making in complex systems.
problem Complex multi-objective decision-making in reinforcement learning.
method Oracle-free and computationally-tractable algorithms for multivariate distributional RL.
result Convergence rates match scalar reward settings and provide insights into reward dimensionality.
Paper establishes DRL for high-dimensional rewards.
problem Intractable reinforcement learning with high-dimensional rewards.
method Theoretical foundations and a novel DRL algorithm.
result Bellman operator contraction in high-dimensional spaces.
Fine-tunes diffusion models to generate diverse samples with high genuine rewards.
problem Reward collapse in finetuning diffusion models.
method Entropy-regularized control against pretrained diffusion models.
result Efficient generation of diverse samples with high genuine rewards.
Extends reinforcement learning alignment to scalar rewards, improving math reasoning.
problem Designing reinforcement learning algorithms for general LLM alignment.
method Introduces f-GRPO and f-HAL, estimating f-divergences between reward-aligned and unaligned distributions.
result Improves math reasoning RLVR tasks and mitigates reward hacking.
A new policy for contextual bandits adapts to reward vector shifts.
problem Learning under reward vector shifts with ordered rewards.
method Adaptive-discretization and optimistic elimination policy.
result Established upper bounds on preference-based regret.
Language models perform worse with implicit reward models than explicit ones.
problem Understanding why implicit reward models generalize worse than explicit ones.
method Investigated the root cause of the generalization gap between IM-RMs and EX-RMs.
result Implicit reward models rely more on superficial token-level cues, leading to worse generalization.
This paper tackles distribution shift in model-based offline RL, proposing a shifts-aware reward method.
problem Distribution shift challenges model-based offline RL by distorting value estimation and policy optimization.
method The paper disentangles the problem into model bias and policy shift, proposing a shifts-aware reward through probabilistic inference.
result The proposed shifts-aware reward method effectively mitigates distribution shift and improves policy optimization.
Agents cooperate to make decisions in multi-armed bandits over a graph.
problem Optimizing decisions in multi-agent multi-armed bandits with shared information.
method Designs consensus-based distributed estimation and cooperative algorithms for group decision-making.
result Achieves group performance close to centralized fusion center.
New bandit algorithms improve sparse reward learning.
problem Sparse rewards hinder learning efficiency in real-world bandit applications.
method Developed algorithms based on Upper Confidence Bound and Thompson Sampling for zero-inflated distributions.
result Empirical performance of new algorithms is superior to existing methods.
New Thompson sampling algorithm reduces regret for exponential family bandits.
problem Minimizing regret in multi-armed bandit problems with exponential family rewards.
method Proposes ExpTS and ExpTS+ algorithms using novel sampling distributions. result Minimizes both finite-time and asymptotic regret for exponential family rewards.
EPIC quantifies reward differences without policy optimization.
problem Distinguishing reward function quality from policy optimization issues.
method EPIC distance to compare reward functions directly.
result EPIC bounds policy training success and regret.
Paper designs a bandit algorithm without reward distribution info.
problem Designing bandit algorithms without reward distribution info.
method Alternates between greedy rule and forced exploration.
result Achieves substantial regret upper bounds.
Best-of-N sampling reveals reward targets from preference data, influencing N and base distribution choices.
problem Understanding reward extraction from Best-of-N preference data and optimal N and base distribution choices.
method Specialized analysis of preference data via induced conditional distribution, deriving reward targets and design principles.
result Reward targets are explicit functions of N and base distribution, and bounded-class minimizers approach these targets as N grows.
Thompson Sampling shows polynomial regret for combinatorial semi-bandits with subgaussian rewards.
problem Finding optimal solutions in combinatorial semi-bandits with suboptimal sampling.
method Proposes Thompson Sampling with polynomial regret for linear combinatorial semi-bandits.
result Demonstrates 'mismatched sampling paradox' where knowing distributions can lead to worse performance.
Motivated by problems in search and detection we present a solution to a Combinatorial Multi-Armed Bandit (CMAB) problem with both heavy-tailed reward distributions and a new class of feedback, filtered semibandit feedback. In a CMAB problem an agent pulls a combination of arms from a set {1,...,k} in each round, g…
The multi-armed bandit (MAB) problem is a classic example of the exploration-exploitation dilemma. It is concerned with maximising the total rewards for a gambler by sequentially pulling an arm from a multi-armed slot machine where each arm is associated with a reward distribution. In static MABs, the reward distributi…
Study noisy rewards in online decision-making with unknown distributions.
problem Learning optimal decisions in online settings with noisy and unknown reward distributions.
method Proposes algorithms integrating learning and decision-making via LCB thresholding.
result Achieves competitive ratios of 1 - 1/e and 1/2 in various settings.
New RL approach uses future state and action visitation measures for better exploration.
problem Improving exploration in reinforcement learning.
method Intrinsic reward based on future state and action visitation measures, using contraction operators.
result Policies achieve good state-action space coverage and high performance.
The paper introduces a new intrinsic reward method for exploration in reinforcement learning.
problem Improving exploration in reinforcement learning agents.
method Intrinsic rewards proportional to the entropy of future state-action features.
result The new objective leads to improved visitation of features within individual trajectories.
New algorithms handle heavy-tailed rewards in reinforcement learning.
problem Learning from heavy-tailed rewards in reinforcement learning.
method Robust mean estimation techniques for constructing algorithms.
result Near-optimal regret bounds achieved in heavy-tailed reward settings.
Training-free method improves large language model sequence quality via reward-guided sampling.
problem Optimizing large language model sequence quality over token likelihood.
method Reward-augmented target distribution combined with Sequential Monte Carlo sampling.
result Significant gains in sequence generation and mathematical reasoning tasks.
We implement momentum strategies using reward-risk measures as ranking criteria based on classical tempered stable distribution. Performances and risk characteristics for the alternative portfolios are obtained in various asset classes and markets. The reward-risk momentum strategies with lower volatility levels outper…
The paper explores how mining costs, rewards, and blockchain security are interconnected.
problem Understanding the interdependencies between mining costs, mining rewards, and blockchain security.
method Theoretical derivation and empirical analysis using daily crypto market data and autoregressive distributed lag approach.
result Cryptocurrency price and mining rewards are intrinsically linked to blockchain security outcomes.
New algorithm for shareable arms with load-dependent rewards in stochastic bandits.
problem Learning optimal play strategy with shareable finite-capacity arms in stochastic bandits.
method Developed a capacity estimator and online learning algorithm for MP-MAB with shareable arms.
result Regret upper bound matches the lower bound, validating the algorithm's performance.
We study the Combinatorial Pure Exploration problem with Continuous and Separable reward functions (CPE-CS) in the stochastic multi-armed bandit setting. In a CPE-CS instance, we are given several stochastic arms with unknown distributions, as well as a collection of possible decisions. Each decision has a reward accor…
Unified approach to time-inconsistent problems with distribution-dependent rewards.
problem Time-inconsistent problems with distribution-dependent rewards in behavioral finance and economics.
method Equilibrium master equation on Wasserstein space, refined derivatives, Itô's formula.
result Unified approach to find equilibrium solutions for time-inconsistent problems.
This work analyzes the value of future reward information in RL.
problem Analyzing the impact of knowing future rewards in reinforcement learning.
method Competitive analysis and worst-case reward distribution.
result Exact ratios between standard RL agents and those with future-reward lookahead.
Improved selection of best outputs from LLMs for better accuracy.
problem BoN fails to reliably find the correct answer with imperfect rewards.
method Majority-of-the-Bests (MoB) selects the mode of a bootstrapped output distribution of BoN.
result MoB consistently improves over BoN in 25 out of 30 setups.
BRAID fine-tunes diffusion models to optimize reward models in offline scenarios.
problem Combining generative modeling and model-based optimization in offline scenarios.
method Conservative fine-tuning of diffusion models using RL to optimize reward models.
result BRAID outperforms existing methods in offline data, avoiding invalid designs.
A novel algorithm minimizes regret in a multi-agent bandit problem with time-varying random graphs and heterogeneous rewards.
problem Minimizing regret in a multi-agent multi-armed bandit problem with time-varying random graphs and heterogeneous rewards.
method Introduces a novel algorithmic framework combining averaging-based consensus with a weighting technique and upper confidence bound.
result Derives optimal instance-dependent regret upper bounds of order logT in both sub-gaussian and sub-exponential environments. AOT aligns LLMs on distributional preferences via optimal transport.
problem Current LLM alignment techniques lack distributional level alignment.
method Alignment via Optimal Transport (AOT) aligns LLMs on unpaired preference data.
result AOT enables alignment by penalizing reward distribution violations.
Framework for optimizing search engine rankings using observational data.
problem Optimizing ranking policies for search engines using limited observational data.
method Formulated expected reward optimization problem, estimated context value distribution, trained ranking policy via Bayesian inference.
result Demonstrated trade-offs in ranking policies trained on empirical reward estimates.
Many reinforcement-learning researchers treat the reward function as a part of the environment, meaning that the agent can only know the reward of a state if it encounters that state in a trial run. However, we argue that this is an unnecessary limitation and instead, the reward function should be provided to the learn…
The recently proposed distributional approach to reinforcement learning (DiRL) is centered on learning the distribution of the reward-to-go, often referred to as the value distribution. In this work, we show that the distributional Bellman equation, which drives DiRL methods, is equivalent to a generative adversarial n…
In this paper we propose a novel framework for decentralized, online learning by many learners. At each moment of time, an instance characterized by a certain context may arrive to each learner; based on the context, the learner can select one of its own actions (which gives a reward and provides information) or reques…
Algorithm improves multi-armed bandit performance by transferring reward samples.
problem Sequential multi-armed bandit problem with changing reward distributions.
method UCB algorithm with reward sample transfer.
result Significant improvement in cumulative regret over standard UCB.
Enhances GFlowNets with distributional approach for risk-sensitive policies.
problem Limited applicability of current GFlowNet framework in handling stochastic reward functions.
method Adopting a distributional paradigm, parameterizing each edge flow through quantile functions, and introducing a risk-sensitive learning algorithm.
result Significant improvement on benchmarks due to enhanced training algorithm, even in deterministic reward settings.
A new method learns continuous guidance weights to improve diffusion model quality and distributional alignment.
problem Improving perceptual quality and distributional alignment of samples from conditional diffusion models.
method Learned continuous guidance weights ωc,(s,t) are used to minimize distributional mismatch and reward guided sampling. result Improvements in Fréchet inception distance (FID) for image generation and better image-prompt alignment in text-to-image applications.
Reward augmented maximum likelihood (RAML), a simple and effective learning framework to directly optimize towards the reward function in structured prediction tasks, has led to a number of impressive empirical successes. RAML incorporates task-specific reward by performing maximum-likelihood updates on candidate outpu…