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.
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 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. This paper proposes a new AED framework for multi-metric experiments with fixed budget.
problem Statistical power challenges in testing multiple metrics simultaneously.
method Two-phase structure: adaptive exploration followed by validation. SHRVar algorithm with relative-variance-based sampling.
result Achieves provable error probability that decreases exponentially.
The paper develops a robust algorithm for contextual bandits with heavy-tailed rewards.
problem Contextual bandits with heavy-tailed rewards.
method Develops an algorithm based on Catoni's estimator for robust statistics, applying it to contextual bandits with general function approximation.
result Establishes regret bounds that depend on cumulative reward variance and logarithmically on the reward range and number of rounds.
Reward models need more than just accuracy for effective RLHF.
problem The effectiveness of reward models in RLHF is not fully understood.
method An optimization perspective to evaluate reward models.
result Reward models with low reward variance can lead to a flat optimization landscape, hindering performance.
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.
Method distills reward and strategies from diverse demonstrators.
problem Reward ambiguity and heterogeneity in human demonstrations.
method Reward network distillation to infer task goal and strategies.
result Better recovery of task and strategy rewards.
A new method resolves non-identifiability in reward modeling using anchor labels.
problem Non-identifiability in reward modeling from pairwise preferences alone.
method Anchor-guided Variance-aware Reward Modeling (AVRM) framework.
result AVRM resolves non-identifiability and improves reward modeling performance.
There exist a number of reinforcement learning algorithms which learnby climbing the gradient of expected reward. Their long-runconvergence has been proved, even in partially observableenvironments with non-deterministic actions, and without the need fora system model. However, the variance of the gradient estimator ha…
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.
Reinforcement Learning (RL) agents require the specification of a reward signal for learning behaviours. However, introduction of corrupt or stochastic rewards can yield high variance in learning. Such corruption may be a direct result of goal misspecification, randomness in the reward signal, or correlation of the rew…
Model shows how centralization occurs in cryptocurrency mining.
problem Centralization of reward and computational power in Bitcoin-like cryptocurrencies.
method Mean field game model to study miner competition and reward distribution.
result Heterogeneity of initial wealth leads to greater imbalance in reward distribution.
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.
Contextual bandits study how reward variance affects regret bounds.
problem Investigating how small reward variance impacts regret bounds in contextual bandits.
method Analyzing two types of adversaries and function approximation complexities.
result Regret bounds are influenced by the eluder dimension and reward variance.
Recent reinforcement learning algorithms, though achieving impressive results in various fields, suffer from brittle training effects such as regression in results and high sensitivity to initialization and parameters. We claim that some of the brittleness stems from variance differences, i.e. when different environmen…
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.
New method for evaluating sequential recommendations with lower variance.
problem Evaluating good sequences of music, video, news, and e-commerce recommendations.
method Proposes a new counterfactual estimator for sequential reward interactions with lower variance and asymptotic unbiasedness.
result Our method outperforms existing methods in bias and data efficiency for sequential track recommendations.
Two algorithms tackle heavy-tailed rewards in reinforcement learning with linear function approximation.
problem Online sequential decision-making with heavy-tailed rewards.
method AdaOFUL and VARA algorithms for linear stochastic bandits and MDPs, using modified adaptive Huber regression.
result Achieved state-of-the-art and variance-aware regret bounds for heavy-tailed rewards.
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. Improved time complexity for parallel stochastic optimization in heterogeneous systems.
problem Time complexity in parallel stochastic optimization for large-scale machine learning models.
method Proposes Rennala MVR, a variance-reduced extension of Rennala SGD based on momentum-based variance reduction.
result Variance reduction improves time complexity in relevant parameter regimes for parallel stochastic optimization in heterogeneous systems.
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 paper optimizes reinsurance contracts with belief differences between insurer and reinsurer.
problem Dynamic reinsurance design with heterogeneous beliefs under mean-variance framework.
method Modeling surplus process, applying partitioned domain optimization, solving HJB system.
result Optimal reinsurance contracts with belief heterogeneity are more complex than standard contracts.
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…
Improved GP bandit algorithms for noiseless, varying noise, and RKHS norms.
problem Minimizing regret in Gaussian process bandits with unknown reward functions.
method New upper bound on maximum posterior variance, refined MVR and PE algorithms.
result Optimal regret bounds for noiseless, varying noise, and RKHS norms.
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…
Paper tackles unknown variances in best-arm identification.
problem Identifying the best arm with unknown variances in Gaussian distributions.
method Two approaches: empirical variance plugging or adapting transportation costs.
result The impact of unknown variances is small on sample complexity.
COCOA improves credit assignment in reinforcement learning by measuring contributions to rewards.
problem Improving sample efficiency in reinforcement learning through better credit assignment methods.
method Counterfactual Contribution Analysis (COCOA) for precise credit assignment.
result COCOA achieves lower bias and variance compared to Hindsight Credit Assignment (HCA), improving reinforcement learning performance.
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. Online learning has traditionally focused on the expected rewards. In this paper, a risk-averse online learning problem under the performance measure of the mean-variance of the rewards is studied. Both the bandit and full information settings are considered. The performance of several existing policies is analyzed, an…
FedGLOMO accelerates FL convergence for non-convex functions.
problem Efficiently solving non-convex optimization problems in federated learning with client heterogeneity.
method Combines global and local momentum updates to reduce variance and improve convergence rate.
result Achieves O ( ε − 1.5 ) \mathcal{O}(ε^{-1.5}) O ( ε − 1.5 ) convergence to ε ε ε -stationary point, compared to O ( ε − 2 ) \mathcal{O}(ε^{-2}) O ( ε − 2 ) . A new method for online personalized learning reduces gradient variance by dynamically selecting peers.
problem Online personalized decentralized learning with statistically heterogeneous clients.
method Gradient-based collaboration criterion allowing clients to dynamically select peers with similar gradients.
result The method acts as a variance reduction method, achieving optimal performance in certain conditions.
Study aims to optimize financial investments by balancing risk and reward efficiently.
problem Balancing risk and reward in dynamic financial investments.
method Proposes a reinforcement learning method to maximize expected quadratic utility, focusing on first and second moments of rewards.
result The proposed method yields MV-efficient policies that maximize expected reward without increasing variance.
New algorithm resists corruption in linear contextual bandits.
problem Adversarial corruption in linear contextual bandits.
method Variance-aware algorithm with multi-level partition and adaptive confidence sets.
result Regret bound of i l d e O ( C 2 d ∑ t = 1 T σ t 2 + C 2 R d T ) ilde{O}(C^2d\sqrt{\sum_{t = 1}^T σ_t^2} + C^2R\sqrt{dT}) i l d e O ( C 2 d ∑ t = 1 T σ t 2 + C 2 R d T ) . A new game-theoretic approach balances downside risk with expected reward.
problem Traditional game theory views risk only from the upside perspective, ignoring downside risk.
method Introduces downside risk aware equilibria (DRAE) based on lower partial moments.
result Successfully finds equilibria that balance downside risk with expected reward.
This paper extends the MAB problem to consider risk-reward tradeoffs.
problem Maximizing reward while accounting for risk in multi-armed bandit problems.
method Introduced the Risk Aware Lower Confidence Bound (RALCB) algorithm to solve the mean-variance MAB problem.
result The RALCB algorithm performs better than the algorithm in Sani et al. (2012) in both independent and dependent scenarios.
Paper proposes a new risk measure (reward volatility) for optimizing financial decisions.
problem Managing uncertainty and volatility in financial decision-making.
method Defines reward volatility, derives policy gradient theorem, develops actor-only algorithm.
result Risk-averse optimization improves both reward volatility and return variance.
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.
New strategy optimally identifies best arm in unknown variance Gaussian bandits.
problem Identifying the best arm in two-armed Gaussian bandits with unknown variances.
method Proposes a Neyman Allocation (NA)-Augmented Inverse Probability weighting (AIPW) strategy to estimate variances and draw arms adaptively.
result Demonstrates asymptotic optimality of the proposed strategy in the small-gap regime.
Optimizes ranking from click feedback in a bandit setting.
problem Learning to rank from Bernoulli click feedback in a bandit setting.
method Variance-aware confidence sets derived from Bernstein and Chernoff bounds for optimal algorithms.
result Optimal algorithms for the case of small mean rewards, improving on previous suboptimal results.
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.
Algorithm identifies best arm in bandit game with variance consideration.
problem Identifying the best arm in a stochastic multi-armed bandit game with varying variances.
method Adaptive algorithm using grouped median elimination to explore gaps and variances.
result Guarantees to output the best arm with probability (1-δ) using optimal number of samples.
USNRT uses tree-structured learning to improve uncertainty quantification of variance networks.
problem Improving uncertainty quantification of variance networks.
method Tree-structured local neural network model that partitions feature space into regions for training region-specific neural networks to predict mean and variance.
result USNRT shows superior performance in estimating uncertainty with variances on UCI datasets compared to recent methods.
Variance plays a crucial role in risk-sensitive reinforcement learning, and most risk measures can be analyzed via variance. In this paper, we consider two law-invariant risks as examples: mean-variance risk and exponential utility risk. With the aid of the state-augmentation transformation (SAT), we show that, the two…
GRPO optimizes LLMs with verifiable rewards, amplifying policy success.
problem Improving LLMs' reasoning under verifiable binary rewards.
method Introduces GRPO, analyzes variants of reward normalization and regularization.
result GRPO amplifies policy success, converging to a fixed point exceeding the reference.