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.
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.
Boosted GFlowNets improve exploration by sequentially training GFlowNets with residual rewards.
problem GFlowNets struggle to evenly explore reward landscapes, leading to poor coverage of high-reward areas.
method Sequential training of an ensemble of GFlowNets, each optimizing a residual reward.
result Boosted GFlowNets achieve better exploration and sample diversity on multimodal benchmarks and peptide design tasks.
Unified framework for human-like decision making in various sequential tasks.
problem Real-life decision-making involves diverse strategies leading to similar outcomes.
method Two-stream reward processing mechanism for flexible and unified models.
result Framework unified MAB, CB, and RL with comparable performance.
Study resource allocation strategies in sequential decisions with unknown rewards.
problem Sequential resource allocation with unknown rewards.
method Design combinatorial multi-armed bandit algorithms for discrete or continuous budgets.
result Prove algorithms achieve logarithmic cumulative regret under semi-bandit feedback.
Algorithm maximizes rewards with a budget and giving up option.
problem Sequential decision-making with stochastic rewards and resource consumption.
method Upper Confidence Bound (UCB) algorithm for maximizing cumulative reward.
result Logarithmic regret bound with improved dependence on problem parameters.
An agent explores indefinitely in an environment with unlimited rewards.
problem Balancing exploration and exploitation in environments with unlimited rewards.
method Simple example of an environment with unbounded rewards and optimal agent behavior.
result An optimal agent always explores to maximize rewards, regardless of accumulated knowledge.
Novel algorithm reduces feature inclusion in online decision-making.
problem Optimizing decision-making for personalized user experiences with fairness.
method Online Batched Sequential Inclusion (OBSI) algorithm for sequential feature inclusion.
result OBSI outperforms other algorithms in terms of regret, relevance of features, and compute.
This work shows how approximate reward models can significantly improve inference-time scaling.
problem Improving the efficiency of inference for large language models.
method Identifying the Bellman error of approximate reward models and using Sequential Monte Carlo (SMC) for inference.
result Approximate reward models can reduce computational complexity from exponential to polynomial in T. 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 extend Bayesian multi-armed bandit (MAB) algorithms beyond their original setting by making use of sequential Monte Carlo (SMC) methods. A MAB is a sequential decision making problem where the goal is to learn a policy that maximizes long term payoff, where only the reward of the executed action is observed. In the …
This work optimizes identifying good arms in nonparametric multi-armed bandits.
problem Efficiently identifying arms with high means in nonparametric settings.
method Combining reward-maximizing sampling with a nonparametric sequential test for anytime-valid labeling.
result Achieves minimax optimal stopping times for identifying arms above a threshold.
Algorithm solves job acceptance problem with random arrivals and values.
problem Decision-making under random job arrivals and values with limited acceptance.
method Proposes Non-Parametric Sequential Allocation (NPSA) algorithm.
result Expected reward converges to optimality as sample size increases.
New algorithms improve multi-task bandit performance by transferring reward samples.
problem Sequential multi-task bandit problems with adjacent similar tasks.
method Two UCB-based algorithms that transfer reward samples between tasks.
result Transfer of reward samples reduces overall regret compared to no transfer.
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.…
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.
New algorithm for multi-armed bandits with delayed, partially observed rewards.
problem Sequential decision-making with delayed feedback.
method Proposed multi-armed bandits with generalized temporally-partitioned rewards, introducing β-spread property.
result Upper bound on performance of TP-UCB-FR-G algorithm improves state of the art.
New approach transfers rewards learned in one environment to reinforcement learning in a new environment.
problem Transfer of rewards learned using inverse reinforcement learning from one environment to a new, different environment.
method Formulate the problem as a joint system of Bellman equations, develop minimax estimators for the target soft-q-function, solve the source and target system of equations jointly. result The coupled approach removes the first-order influence of source Bellman residual error compared to the sequential approach.
Self-distillation improves constrained language generation by aligning models with target distributions.
problem Sparse and uninformative reward signals in constrained generation settings.
method Iteratively refining the base model through self-distillation, incorporating learned twist functions and proposals.
result Substantial gains in generation quality through improved model alignment with target distributions.
Study on optimizing task allocation for agents receiving proposals sequentially.
problem Optimizing task allocation for agents receiving proposals sequentially.
method An agent receives task proposals sequentially and can either accept or reject a proposal. The study considers two scenarios: known reward function but unknown task duration distribution, and unknown reward function.
result Regret incurred by the agent in both scenarios.
CRB tackles rising rewards in combinatorial online learning.
problem Rising rewards in combinatorial online learning.
method CRB framework and CRUCB algorithm.
result Empirical and theoretical validation of CRUCB's effectiveness.
Improves inference-time alignment for diffusion models without updating weights.
problem Aligning diffusion models without updating weights for high-reward outputs.
method Trust-Region Iterative Twisted Sequential Monte Carlo (TRI-TSMC) for variance reduction and efficiency.
result Improves primary alignment objectives on text generation tasks.
Proposes a real-time anomaly detection system using IRL.
problem Real-time anomaly detection in sequential data.
method Uses inverse reinforcement learning to infer reward function and evaluate anomalies.
result Effective in identifying anomalies in real-world data.
Study personalizes user experience to maximize rewards with patience budget.
problem Maximizing rewards for a platform while respecting user patience.
method Proposes bandit algorithms for sequential choice with feedback models.
result Upper and lower bounds on regret of order O(N2/3) and Ω(N2/3). New algorithm uses machine learning to predict rewards for decision-making problems.
problem Sequential decision-making under uncertainty with scarce online data.
method Machine Learning-Assisted Upper Confidence Bound (MLA-UCB) algorithm.
result Proves to improve cumulative regret even with biased surrogate rewards.
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.
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.
PQR estimates reward functions from actions and states without assuming state-only rewards.
problem Estimating reward functions from actions and states without state-only assumptions.
method Deep learning approach that sequentially estimates policy, Q-function, and reward.
result PQR uniquely recovers true reward with known transitions and bounds error with unknown transitions.
In this paper we investigate the Follow the Regularized Leader dynamics in sequential imperfect information games (IIG). We generalize existing results of Poincaré recurrence from normal-form games to zero-sum two-player imperfect information games and other sequential game settings. We then investigate how adapting th…
This paper proposes a method to evaluate policies using quantile metrics, improving upon existing mean-based approaches.
problem Evaluating policies using mean-based metrics ignores the variability of outcomes, especially in skewed reward distributions.
method The paper introduces a doubly-robust inference procedure for quantile off-policy evaluation using deep conditional generative learning.
result The proposed estimator outperforms classical OPE estimators for mean outcomes in heavy-tailed reward distributions.
New method reduces regret in budgeted learning problems.
problem Decision-making with limited reward queries.
method Confidence-Budget Matching (CBM) principle.
result CBM-based algorithms perform well in adversarial settings.
The paper studies how to improve language model inference using particle filtering.
problem Understanding the accuracy-cost tradeoffs of inference-time methods for large language models.
method Introduces particle filtering algorithms like Sequential Monte Carlo (SMC) to study language model inference.
result Identifies criteria enabling non-asymptotic guarantees for SMC and fundamental limits faced by all particle filtering methods.
The Combinatorial Multi-Armed Bandit problem is a sequential decision-making problem in which an agent selects a set of arms on each round, observes feedback for each of these arms and aims to maximize a known reward function of the arms it chose. While previous work proved regret upper bounds in this setting for gener…
A novel framework refines diffusion models iteratively for better downstream reward optimization.
problem Optimizing reward functions during inference of diffusion models.
method Iterative refinement process with noising and reward-guided denoising steps.
result Superior empirical performance in protein and DNA design.
New batched Langevin Thompson Sampling reduces communication costs for sequential decision making.
problem Efficiently learning unknown reward distributions and transition dynamics in batched settings.
method Langevin Thompson Sampling with logarithmic communication costs.
result Order-optimal regret guarantees for stochastic MABs and RL.
Unified LP framework for offline reward learning from human demonstrations and feedback.
problem Reward learning from human demonstrations and feedback with robustness and sample efficiency.
method A novel linear programming framework for offline reward learning.
result Unified LP framework achieves better performance compared to MLE.
In many sequential decision making tasks, it is challenging to design reward functions that help an RL agent efficiently learn behavior that is considered good by the agent designer. A number of different formulations of the reward-design problem, or close variants thereof, have been proposed in the literature. In this…
New method optimizes portfolios by dynamically integrating ESG constraints.
problem Static ESG scores mismatch sequential portfolio decisions.
method MACF-X, a family of adapters that learns ESG costs from multimodal evidence.
result Reduces tail ESG budget pressure while maintaining financial performance.
Contextual multi-armed bandit (MAB) algorithms have been shown promising for maximizing cumulative rewards in sequential decision tasks such as news article recommendation systems, web page ad placement algorithms, and mobile health. However, most of the proposed contextual MAB algorithms assume linear relationships be…
Paper introduces a novel reward function for noisy financial markets using imitation learning.
problem Noisy reward function in financial markets hinders RL agent performance.
method Integrates imitation learning feedback with reinforcement learning to improve reward function design.
result Improves financial performance metrics compared to traditional benchmarks and RL agents.
State of the art deep reinforcement learning algorithms take many millions of interactions to attain human-level performance. Humans, on the other hand, can very quickly exploit highly rewarding nuances of an environment upon first discovery. In the brain, such rapid learning is thought to depend on the hippocampus and…
OMLE combines optimism and MLE for efficient sequential decision making.
problem Efficiently solving sequential decision making problems, especially in partially observable settings.
method Combines optimism for exploration and maximum likelihood estimation for model learning.
result OMLE learns near-optimal policies for a wide range of sequential decision making problems.
Improved Bayesian regret bound for linear Thompson sampling with general distributions.
problem Proving an improved Bayesian regret bound for linear Thompson sampling with general distributions.
method Generalized elliptical potential lemma for non-Gaussian noise and prior distributions.
result Minimax optimal regret bound for changing action sets with general prior and noise distributions.
Novel framework for risk-sensitive reinforcement learning using martingale decomposition.
problem Risk sensitivity in sequential decision-making with uncertain rewards.
method Martingale decomposition and chaotic variation for reward uncertainty, integrated into model-free reinforcement learning algorithms.
result Demonstrated relevance of risk-sensitive reinforcement learning in grid world and portfolio optimization problems.
A new method for identifying the best arm in multi-armed bandits with mediator feedback.
problem Sequential decision-making with unknown mediator policies.
method Best-arm identification under mediators' feedback (BAI-MF) with statistical lower bound and sequential decision-making strategy.
result The proposed algorithm matches the lower bound on sample complexity for identifying the best arm.
Reinforcement learning aids decision-making in economics and finance.
problem Optimal decision-making in dynamic, uncertain environments.
method Reinforcement learning algorithms to learn optimal policies.
result Deep learning enhances solving complex behavioral problems.
This thesis analyzes MACL systems with low-regret learning algorithms for sequential decision making.
problem Designing efficient learning algorithms for multi-agent cooperative systems to minimize regret.
method Analyzes and develops algorithms for cooperative multi-agent multi-armed bandit problems and online convex optimization in distributed settings.
result Presented regret lower bounds and efficient algorithms for achieving these bounds, providing guidance on communication protocols.
In this paper, we investigate cost-aware joint learning and optimization for multi-channel opportunistic spectrum access in a cognitive radio system. We investigate a discrete time model where the time axis is partitioned into frames. Each frame consists of a sensing phase, followed by a transmission phase. During the …