Method tackles uncertainty in reward models for LLMs from heterogeneous human feedback.
problem Uncertainty in reward models for LLMs from heterogeneous human feedback.
method Heterogeneous preference framework and alternating gradient descent algorithm.
result Established theoretical guarantees for estimator convergence and asymptotic distribution.
New algorithm estimates treatment effects for more efficient contextual bandits.
problem Contextual bandits struggle with action-independent reward redundancies.
method Reduces contextual bandits to heterogeneous treatment effect estimation.
result Heterogeneous treatment effect estimation leads to more efficient model estimation.
Reinforcement learning (RL) has achieved tremendous success as a general framework for learning how to make decisions. However, this success relies on the interactive hand-tuning of a reward function by RL experts. On the other hand, inverse reinforcement learning (IRL) seeks to learn a reward function from readily-obt…
A fair reward system boosts participation in federated learning.
problem Fairness in federated learning among competitive agents with siloed data.
method Hierarchically fair federated learning (HFFL) framework with proportional rewards based on contribution levels.
result Efficacy of HFFL in maintaining fairness and facilitating federated learning in competitive settings.
New algorithms improve best-arm identification with varying rewards.
problem Identifying the best arm with varying reward variances in fixed budget.
method Proposed two algorithms: SHVar for known variances, SHAdaVar for unknown variances; uses non-uniform budget allocation.
result Bounding misidentification probabilities for both algorithms.
Two novel methods identify influential features in CMABs for better reward distribution.
problem Suboptimal features degrade rewards, interpretability, and efficiency in CMABs.
method Heterogeneous Incremental Effect (HIE) and Heterogeneous Distribution Divergence (HDD) methods.
result Consistent ability to identify influential HTE features, enhancing CMAB performance.
New strategies improve multi-agent decision-making on irregular networks.
problem Maximizing group reward in multi-agent settings with heterogeneous strategies.
method Design and analysis of heterogeneous explore-exploit strategies for multi-star networks.
result Group performance improves under heterogeneous strategies compared to homogeneous strategies.
New framework tackles stochastic latent subgroup heterogeneity in online decision-making.
problem Stochastic latent heterogeneity in online decision-making where individual responses vary with unobserved subgroups.
method Latent heterogeneous bandit framework using EM-greedy algorithm to learn subgroup probabilities and reward parameters.
result Achieves optimal estimation and classification guarantees, revealing a fundamental stochastic barrier in online decision-making.
A multi-player bandit system resists adversarial attacks with near-optimal regret.
problem Adversaries attempt to manipulate rewards in a multi-player multi-armed bandit game.
method Players communicate a single bit to resist attacks, achieving near-optimal regret.
result Achieves near-optimal regret of O ( log 1 + δ T + W ) O(\log^{1+δ}T + W) O ( log 1 + δ T + W ) , where W W W is the total time of adversarial attacks. PRISM integrates diverse rewards in MORL, improving sample efficiency and Pareto coverage.
problem Heterogeneous MORL where dense objectives dominate, leading to poor sample efficiency.
method PRISM uses reflectional symmetry and ReSymNet to reconcile temporal-frequency mismatches and accelerate exploration.
result PRISM consistently outperforms sparse-reward baselines and oracles, achieving significant Pareto gains.
This work frames reward modelling from preferences as a causal problem.
problem Reward modelling from preference data for AI alignment.
method Causal inference approach to identify challenges and assumptions.
result Causally-inspired approaches improve model robustness.
We introduce reinforcement learning for heterogeneous teams in which rewards for an agent are additively factored into local costs, stimuli unique to each agent, and global rewards, those shared by all agents in the domain. Motivating domains include coordination of varied robotic platforms, which incur different costs…
Distributed learning adapts to diverse devices, improving performance.
problem Training neural networks on devices with varying capabilities and resources.
method Each device trains a customized neural network, sharing parameters with others.
result Achieves higher rewards on more powerful devices without sacrificing weaker ones.
We consider a fully decentralized multi-player stochastic multi-armed bandit setting where the players cannot communicate with each other and can observe only their own actions and rewards. The environment may appear differently to different players, i.e. \textit{i.e.} i.e. , the reward distributions for a given arm are heterog…
We propose a mean field game model to study the question of how centralization of reward and computational power occur in Bitcoin-like cryptocurrencies. Miners compete against each other for mining rewards by increasing their computational power. This leads to a novel mean field game of jump intensity control, which we…
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 log T \log{T} log T in both sub-gaussian and sub-exponential environments. Heterogeneous SVO leads to diverse policies in sequential social dilemmas.
problem Understanding how diverse social value orientations affect behavior in sequential social dilemmas.
method Extending prior reinforcement learning studies, we instantiated heterogeneous SVO in a sequential social dilemma setting and measured task-specific diversity metrics.
result Heterogeneous SVO leads to meaningfully diverse policies across various incentive structures.
Algorithm aggregates rewards from multiple players to learn related tasks in online bandit learning.
problem Learning related but slightly different tasks in an online setting with heterogeneous feedback.
method RobustAgg ( ε ) (ε) ( ε ) algorithm that aggregates rewards from different players. result Achieves instance-dependent regret guarantees and nearly matching lower bounds.
Paper closes the gap in MP-MAB problems with novel adaptive communication and exploration.
problem Closing the gap between decentralized MP-MAB and natural centralized lower bound.
method BEACON: Batched Exploration with Adaptive COmmunicatioN, incorporating ADC and batched exploration.
result Proves logarithmic regret for a generalized MP-MAB problem.
New algorithm tackles multi-agent bandits with heavy-tailed data.
problem Maximizing system performance in multi-agent settings with heavy-tailed data.
method Algorithm exploits hub-like structures and synchronization among clients.
result Regret bound of O ( M 1 − 1 α log T ) O(M^{1 -\frac{1}α} \log{T}) O ( M 1 − α 1 log T ) for homogeneous settings, O ( M log T ) O(M \log{T}) O ( M log T ) for heterogeneous. FedSARSA converges with heterogeneous agents, achieving linear speed-up.
problem Convergence analysis of Federated SARSA with heterogeneous agents.
method Linear function approximation, local training, multi-step error expansion.
result FedSARSA achieves linear speed-up with respect to the number of agents.
Providing a suitable reward function to reinforcement learning can be difficult in many real world applications. While inverse reinforcement learning (IRL) holds promise for automatically learning reward functions from demonstrations, several major challenges remain. First, existing IRL methods learn reward functions f…
Imitation learning is an effective alternative approach to learn a policy when the reward function is sparse. In this paper, we consider a challenging setting where an agent and an expert use different actions from each other. We assume that the agent has access to a sparse reward function and state-only expert observa…
The paper develops a reinforcement learning model to estimate ad impact considering delayed and cumulative effects.
problem Accurately estimating ad impact considering delayed and long-term effects, cumulative impacts, and customer heterogeneity.
method Modeling ad bidding as a Contextual Markov Decision Process (CMDP) with delayed Poisson rewards, proposing a two-stage maximum likelihood estimator and reinforcement learning algorithm.
result Achieves a near-optimal regret bound of O ~ ( d H 2 T ) \tilde{O}{(dH^2\sqrt{T})} O ~ ( d H 2 T ) , validating the approach through simulation experiments. Paper proposes a method to optimize policies for diverse individuals using heterogeneous data.
problem Learning optimal policies for a heterogeneous population from pre-collected data.
method Individualized offline policy optimization framework for heterogeneous MDPs.
result The proposed P4L algorithm achieves a fast rate of average regret.
A new algorithm optimizes local objectives in federated learning with heterogeneous clients.
problem Optimizing local objectives in federated learning with heterogeneous client data.
method Proposes PF-PNE algorithm with double elimination strategy.
result PF-PNE algorithm optimizes local objectives with arbitrary heterogeneity and protects client data confidentiality.
Proposes a framework for energy-efficient AIGC workload scheduling in cloud data centers.
problem Challenges of scheduling AIGC workloads for energy efficiency and quality control.
method Joint energy management and coordinated AIGC workload scheduling framework with diffusion model-aided reward shaping.
result Effective learning of scheduling policies under sparse environmental feedback.
RoME optimizes mobile health interventions by modeling user and time-specific effects.
problem Challenges in optimizing mobile health interventions due to participant heterogeneity, nonstationarity, and nonlinear relationships.
method RoME uses a Robust Mixed-Effects contextual bandit algorithm with random effects, network cohesion penalties, and debiased machine learning.
result RoME achieves robust regret bounds even with complex baseline rewards, demonstrating superior performance in simulations and studies.
The paper explores how to apply causal knowledge across different datasets to improve learning.
problem How to apply causal knowledge across different datasets to improve learning.
method Investigates the structural causal bandit with transportability, fusing priors from source environments to enhance learning in the deployment setting.
result Achieves a sub-linear regret bound with an explicit dependence on informativeness of prior data, potentially outperforming standard bandit approaches.
Adaptive reward models capture individual preferences from human feedback.
problem Learning a reward model that can be specialised to a user.
method Empirical risk minimisation and PAC bound analysis.
result Adaptive reward models benefit from the heterogeneity of user preferences.
Paper tackles best arm identification with cost consideration.
problem Best arm identification with cost consideration in product development.
method Derives a theoretical lower bound and proposes algorithms CTAS and CO.
result Simple algorithms can deliver near-optimal performance.
Modeling decision-making dynamics in MDD patients using RL-HMM.
problem Characterize reward learning strategies in MDD patients.
method Proposed RL-HMM framework to analyze reward-based decision-making.
result MDD patients show reduced engagement in RL compared to healthy controls.
Algorithm maximizes total reward in multi-agent bandits with adversarial corruptions.
problem Maximizing total reward in multi-agent bandits with adversarial corruptions.
method Proposes a cooperative learning algorithm robust to adversarial corruptions.
result Demonstrates an additive O ( ( L / L min ) C ) O((L / L_{\min}) C) O (( L / L m i n ) C ) regret term for an adversary with unknown corruption budget. Optimizes user marketing campaigns to balance cost and effectiveness.
problem Lack of methods to optimize marketing campaigns considering cost and effectiveness.
method Proposes a treatment effect optimization algorithm using deep learning to balance cost and effectiveness.
result Demonstrates superior performance in cost-efficiency and real-world business value.
New algorithm for multi-player bandits with selfish players, achieving logarithmic regret.
problem Challenges of robustness to selfish players in multi-player bandits.
method First algorithm robust to selfish players achieving logarithmic regret, with or without collision observation.
result Achieved logarithmic regret for robust algorithms to selfish players in multi-player bandits.
The paper tackles misspecification in contextual bandits by incorporating arm-specific variables.
problem Misspecification in contextual bandits due to unexplained inter-arm heterogeneity.
method Develops robust contextual bandit algorithms (RoLinUCB and RoLinTS) that incorporate arm-specific variables to address misspecification.
result The developed algorithms bound the n n n -round Bayes regret and show superior performance in various misspecification scenarios. LoCo-RLHF models diverse human feedback with contextual information.
problem Heterogeneous human feedback from diverse contexts and preferences.
method Low-rank contextual preference model, PRS policy.
result LoCo-RLHF achieves tighter sub-optimality gap than existing methods.
RLHF uses human feedback to train AI models, posing statistical challenges.
problem Aligning AI models with human preferences using noisy, subjective feedback.
method Supervised fine-tuning, reward modeling, policy optimization, statistical ideas.
result Statistical methods for reward function learning and policy optimization.
A collaborative algorithm reduces regret in federated linear contextual bandits.
problem Optimizing decision-making in federated learning with heterogeneous data.
method Fed-PE algorithm, leveraging geometric structure of rewards, multi-client G-optimal design.
result Achieves near-optimal regrets with logarithmic communication costs.
A new algorithm reduces communication costs for collaborative decision-making across clients.
problem Collaborative decision-making with sparse rewards and heterogeneous contexts.
method Federated Lasso algorithm for sparse linear contextual bandits.
result Achieves near-optimal regret with logarithmic communication costs.
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.
Response time improves alignment with diverse human preferences.
problem Standard aggregation of feedback ignores heterogeneity and anonymity.
method Augmenting feedback with response time data and modeling decisions with DDM.
result Estimator of heterogeneous preferences converges to true average preference.
New algorithm optimizes decision-making for complex systems with varying parameters.
problem Optimizing decisions in systems with varying parameters and heterogeneous restlessness.
method Model Predictive Control (MPC) approach with randomized rounding for heterogeneous RMABs.
result Achieves an O ( log N 1 / N ) O(\log N\sqrt{1/N}) O ( log N 1/ N ) optimality gap in infinite time average reward problems. Kernel method estimates long-term effects from short-term data.
problem Estimating long-term effects from short-term data in continuous actions.
method Kernel ridge regression to embed and extrapolate long-term effects.
result Uniform consistency and nonasymptotic error bounds for the estimator.
We study contextual bandits with budget and time constraints, referred to as constrained contextual bandits.The time and budget constraints significantly complicate the exploration and exploitation tradeoff because they introduce complex coupling among contexts over time.Such coupling effects make it difficult to obtai…
DRO-REBEL improves LLM alignment by robustly updating models online.
problem Overfitting and drifting of LLMs during RLHF.
method DRO-REBEL uses type- p p p Wasserstein, KL, and χ 2 χ^2 χ 2 ambiguity sets for robust online updates. result DRO-REBEL achieves faster convergence and better performance than prior methods.
We study a general problem of allocating limited resources to heterogeneous customers over time under model uncertainty. Each type of customer can be serviced using different actions, each of which stochastically consumes some combination of resources, and returns different rewards for the resources consumed. We consid…
ODC protocol improves learning in asynchronous multi-agent bandits.
problem Cooperative multi-agent bandits with unknown, irregular pull times.
method ODC protocol for on-demand communication between agents.
result ODC protocol reduces communication complexity based on empirical pull times.