Search Results for author:
Found 19 papers, 9 papers with code
Filtered Direct Preference Optimization
This paper addresses the issue of text quality within the preference dataset by focusing on direct preference optimization (DPO), an increasingly adopted reward-model-free RLHF method.
Regularized Best-of-N Sampling to Mitigate Reward Hacking for Language Model Alignment
In this research, we propose Regularized Best-of-N (RBoN), a variant of BoN that aims to mitigate reward hacking by incorporating a proximity term in response selection, similar to preference learning techniques.
Scalable and Provably Fair Exposure Control for Large-Scale Recommender Systems
Typical recommendation and ranking methods aim to optimize the satisfaction of users, but they are often oblivious to their impact on the items (e. g., products, jobs, news, video) and their providers.
Return-Aligned Decision Transformer
Decision Transformer (DT) optimizes a policy that generates actions conditioned on the target return through supervised learning and is equipped with a mechanism to control the agent using the target return.
Learning Fair Division from Bandit Feedback
This work addresses learning online fair division under uncertainty, where a central planner sequentially allocates items without precise knowledge of agents' values or utilities.
Model-Based Minimum Bayes Risk Decoding for Text Generation
MBR decoding selects a hypothesis from a pool of hypotheses that has the least expected risk under a probability model according to a given utility function.
Why Guided Dialog Policy Learning performs well? Understanding the role of adversarial learning and its alternative
One way to estimate rewards from collected data is to train the reward estimator and dialog policy simultaneously using adversarial learning (AL).
Adaptively Perturbed Mirror Descent for Learning in Games
This paper proposes a payoff perturbation technique for the Mirror Descent (MD) algorithm in games where the gradient of the payoff functions is monotone in the strategy profile space, potentially containing additive noise.
Exploration of Unranked Items in Safe Online Learning to Re-Rank
In this paper, we propose a safe OLTR algorithm that efficiently exchanges one of the items in the current ranking with an item outside the ranking (i. e., an unranked item) to perform exploration.
Fair Matrix Factorisation for Large-Scale Recommender Systems
However, the intrinsic nature of fairness destroys the separability of optimisation subproblems for users and items, which is an essential property of conventional scalable algorithms, such as implicit alternating least squares (iALS).
Last-Iterate Convergence with Full and Noisy Feedback in Two-Player Zero-Sum Games
This paper proposes Mutation-Driven Multiplicative Weights Update (M2WU) for learning an equilibrium in two-player zero-sum normal-form games and proves that it exhibits the last-iterate convergence property in both full and noisy feedback settings.
Mutation-Driven Follow the Regularized Leader for Last-Iterate Convergence in Zero-Sum Games
In this study, we consider a variant of the Follow the Regularized Leader (FTRL) dynamics in two-player zero-sum games.
Policy Gradient Algorithms with Monte Carlo Tree Learning for Non-Markov Decision Processes
In this work, we first introduce Monte Carlo Tree Learning (MCTL), an adaptation of MCTS for online RL setups.
Anytime Capacity Expansion in Medical Residency Match by Monte Carlo Tree Search
Constructing a good search tree representation significantly boosts the performance of the proposed method.
A Practical Guide of Off-Policy Evaluation for Bandit Problems
Based on the properties of the evaluation policy, we categorize OPE situations.
Thresholded Lasso Bandit
In this paper, we revisit the regret minimization problem in sparse stochastic contextual linear bandits, where feature vectors may be of large dimension $d$, but where the reward function depends on a few, say $s_0\ll d$, of these features only.
Mean-Variance Efficient Reinforcement Learning by Expected Quadratic Utility Maximization
To achieve this purpose, we train an agent to maximize the expected quadratic utility function, a common objective of risk management in finance and economics.
Off-Policy Exploitability-Evaluation in Two-Player Zero-Sum Markov Games
The proposed estimators project exploitability that is often used as a metric for determining how close a policy profile (i. e., a tuple of policies) is to a Nash equilibrium in two-player zero-sum games.
A Simple Heuristic for Bayesian Optimization with A Low Budget
The aim of black-box optimization is to optimize an objective function within the constraints of a given evaluation budget.
