Search Results for author:
Found 21 papers, 4 papers with code
Reward Model Learning vs. Direct Policy Optimization: A Comparative Analysis of Learning from Human Preferences
Moreover, we extend our analysis to the approximate optimization setting and derive exponentially decaying convergence rates for both RLHF and DPO.
Corruption-Robust Offline Two-Player Zero-Sum Markov Games
We note that we are the first to provide such a characterization of the problem of learning approximate Nash Equilibrium policies in offline two-player zero-sum Markov games under data corruption.
Performative Reinforcement Learning in Gradually Shifting Environments
Unlike PRL, our framework allows to model scenarios where the environment gradually adjusts to a deployed policy.
Learning the Expected Core of Strictly Convex Stochastic Cooperative Games
Reward allocation, also known as the credit assignment problem, has been an important topic in economics, engineering, and machine learning.
Corruption Robust Offline Reinforcement Learning with Human Feedback
We aim to design algorithms that identify a near-optimal policy from the corrupted data, with provable guarantees.
Agent-Specific Effects: A Causal Effect Propagation Analysis in Multi-Agent MDPs
These challenges are particularly prominent in the context of multi-agent sequential decision-making, where the causal effect of an agent's action on the outcome depends on how other agents respond to that action.
Markov Decision Processes with Time-Varying Geometric Discounting
We take a game-theoretic perspective -- whereby each time step is treated as an independent decision maker with their own (fixed) discount factor -- and we study the subgame perfect equilibrium (SPE) of the resulting game as well as the related algorithmic problems.
Sequential Principal-Agent Problems with Communication: Efficient Computation and Learning
In this model, the principal and the agent interact in a stochastic environment, and each is privy to observations about the state not available to the other.
Implicit Poisoning Attacks in Two-Agent Reinforcement Learning: Adversarial Policies for Training-Time Attacks
In this paper, we study targeted poisoning attacks in a two-agent setting where an attacker implicitly poisons the effective environment of one of the agents by modifying the policy of its peer.
Online Reinforcement Learning with Uncertain Episode Lengths
We show that minimizing regret with this new general discounting is equivalent to minimizing regret with uncertain episode lengths.
Socially Fair Reinforcement Learning
We consider the problem of minimizing regret with respect to the fair policies maximizing three different fair objectives -- minimum welfare, generalized Gini welfare, and Nash social welfare.
Performative Reinforcement Learning
We introduce the framework of performative reinforcement learning where the policy chosen by the learner affects the underlying reward and transition dynamics of the environment.
Learning Tensor Representations for Meta-Learning
Prior works on learning linear representations for meta-learning assume that there is a common shared representation across different tasks, and do not consider the additional task-specific observable side information.
Feature-based Individual Fairness in k-Clustering
Ensuring fairness in machine learning algorithms is a challenging and essential task.
Surprisingly Popular Voting Recovers Rankings, Surprisingly!
A clever recent approach, \emph{surprisingly popular voting}, elicits additional information from the individuals, namely their \emph{prediction} of other individuals' votes, and provably recovers the ground truth even when experts are in minority.
Meta-Learning with Graph Neural Networks: Methods and Applications
Graph Neural Networks (GNNs), a generalization of deep neural networks on graph data have been widely used in various domains, ranging from drug discovery to recommender systems.
Adversarial Blocking Bandits
On the other hand, when B_T is not known, we show that the dynamic approximate regret of RGA-META is at most O((K+\tilde{D})^{1/4}\tilde{B}^{1/2}T^{3/4}) where \tilde{B} is the maximal path variation budget within each batch of RGA-META (which is provably in order of o(\sqrt{T}).
Ensuring Fairness Beyond the Training Data
In this work, we develop classifiers that are fair not only with respect to the training distribution, but also for a class of distributions that are weighted perturbations of the training samples.
Efficient and Thrifty Voting by Any Means Necessary
We take an unorthodox view of voting by expanding the design space to include both the elicitation rule, whereby voters map their (cardinal) preferences to votes, and the aggregation rule, which transforms the reported votes into collective decisions.
Weighted Tensor Completion for Time-Series Causal Inference
We model the potential outcomes as a three-dimensional tensor of low rank, where the three dimensions correspond to the agents, time periods and the set of possible histories.
Calibrated Fairness in Bandits
In addition, we define the {\em fairness regret}, which corresponds to the degree to which an algorithm is not calibrated, where perfect calibration requires that the probability of selecting an arm is equal to the probability with which the arm has the best quality realization.
