Search Results for author:
Found 39 papers, 6 papers with code
A Minimax Approach to Ad Hoc Teamwork
We propose a minimax-Bayes approach to Ad Hoc Teamwork (AHT) that optimizes policies against an adversarial prior over partners, explicitly accounting for uncertainty about partners at time of deployment.
Probably Correct Optimal Stable Matching for Two-Sided Markets Under Uncertainty
We consider a learning problem for the stable marriage model under unknown preferences for the left side of the market.
Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret
First, we show that the Posterior Sampling-based RL (PSRL) yields sublinear regret if the data distributions satisfy LSI under some mild additional assumptions.
Strategic Linear Contextual Bandits
Motivated by the phenomenon of strategic agents gaming a recommender system to maximize the number of times they are recommended to users, we study a strategic variant of the linear contextual bandit problem, where the arms can strategically misreport privately observed contexts to the learner.
Eliciting Kemeny Rankings
Furthermore, if all agents' preferences are strict rankings over the alternatives, we provide means to prune confidence intervals and thereby guide a more efficient elicitation.
Bandits Meet Mechanism Design to Combat Clickbait in Online Recommendation
We study a strategic variant of the multi-armed bandit problem, which we coin the strategic click-bandit.
Minimax-Bayes Reinforcement Learning
While the Bayesian decision-theoretic framework offers an elegant solution to the problem of decision making under uncertainty, one question is how to appropriately select the prior distribution.
Reinforcement Learning in the Wild with Maximum Likelihood-based Model Transfer
Then, we propose a generic two-stage algorithm, MLEMTRL, to address the MTRL problem in discrete and continuous settings.
Environment Design for Inverse Reinforcement Learning
Even with abundant data, current inverse reinforcement learning methods that focus on learning from a single environment can fail to handle slight changes in the environment dynamics.
Risk-Sensitive Bayesian Games for Multi-Agent Reinforcement Learning under Policy Uncertainty
In existing literature, the risk in stochastic games has been studied in terms of the inherent uncertainty evoked by the variability of transitions and actions.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Interactive Inverse Reinforcement Learning for Cooperative Games
How should the first agent act in order to learn the joint reward function as quickly as possible and so that the joint policy is as close to optimal as possible?
High-dimensional near-optimal experiment design for drug discovery via Bayesian sparse sampling
We study the problem of performing automated experiment design for drug screening through Bayesian inference and optimisation.
Adaptive Belief Discretization for POMDP Planning
We instead propose an adaptive belief discretization scheme, and give its associated planning error.
On Meritocracy in Optimal Set Selection
Typically, merit is defined with respect to some intrinsic measure of worth.
SENTINEL: Taming Uncertainty with Ensemble-based Distributional Reinforcement Learning
In this paper, we consider risk-sensitive sequential decision-making in Reinforcement Learning (RL).
Inferential Induction: A Novel Framework for Bayesian Reinforcement Learning
Bayesian reinforcement learning (BRL) offers a decision-theoretic solution for reinforcement learning.
Near-optimal Bayesian Solution For Unknown Discrete Markov Decision Process
We derive the first polynomial time Bayesian algorithm, BUCRL{} that achieves up to logarithm factors, a regret (i. e the difference between the accumulated rewards of the optimal policy and our algorithm) of the optimal order $\tilde{\mathcal{O}}(\sqrt{DSAT})$.
Epistemic Risk-Sensitive Reinforcement Learning
The risk-averse behavior is then compared with the behavior of the optimal risk-neutral policy in environments with epistemic risk.
Near-Optimal Online Egalitarian learning in General Sum Repeated Matrix Games
We study two-player general sum repeated finite games where the rewards of each player are generated from an unknown distribution.
Differential Privacy for Multi-armed Bandits: What Is It and What Is Its Cost?
We derive and contrast lower bounds on the regret of bandit algorithms satisfying these definitions.
Near-optimal Optimistic Reinforcement Learning using Empirical Bernstein Inequalities
We study model-based reinforcement learning in an unknown finite communicating Markov decision process.
Model-based Reinforcement Learning
reinforcement-learning
+2
Randomised Bayesian Least-Squares Policy Iteration
We introduce Bayesian least-squares policy iteration (BLSPI), an off-policy, model-free, policy iteration algorithm that uses the Bayesian least-squares temporal-difference (BLSTD) learning algorithm to evaluate policies.
Bayesian Reinforcement Learning via Deep, Sparse Sampling
We address the problem of Bayesian reinforcement learning using efficient model-based online planning.
On The Differential Privacy of Thompson Sampling With Gaussian Prior
This compares favorably to the previous result for Thompson Sampling in the literature ((Mishra & Thakurta, 2015)) which adds a term of $\mathcal{O}(\frac{K \ln^3 T}{\epsilon^2})$ to the regret in order to achieve the same privacy level.
Multi-View Decision Processes: The Helper-AI Problem
We consider a two-player sequential game in which agents have the same reward function but may disagree on the transition probabilities of an underlying Markovian model of the world.
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.
Bayesian fairness
We consider the problem of how decision making can be fair when the underlying probabilistic model of the world is not known with certainty.
Achieving Privacy in the Adversarial Multi-Armed Bandit
This allows us to reach $\mathcal{O}{(\sqrt{\ln T})}$-DP, with a regret of $\mathcal{O}{(T^{2/3})}$ that holds against an adaptive adversary, an improvement from the best known of $\mathcal{O}{(T^{3/4})}$.
Thompson Sampling For Stochastic Bandits with Graph Feedback
We present a novel extension of Thompson Sampling for stochastic sequential decision problems with graph feedback, even when the graph structure itself is unknown and/or changing.
On the Differential Privacy of Bayesian Inference
We study how to communicate findings of Bayesian inference to third parties, while preserving the strong guarantee of differential privacy.
Algorithms for Differentially Private Multi-Armed Bandits
This is a significant improvement over previous results, which only achieve poly-log regret $O(\epsilon^{-2} \log^{2} T)$, because of our use of a novel interval-based mechanism.
Generalised Entropy MDPs and Minimax Regret
Bayesian methods suffer from the problem of how to specify prior beliefs.
Probabilistic inverse reinforcement learning in unknown environments
To do so, we extend previous probabilistic approaches for inverse reinforcement learning in known MDPs to the case of unknown dynamics or opponents.
Probabilistic inverse reinforcement learning in unknown environments
To do so, we extend previous probabilistic approaches for inverse reinforcement learning in known MDPs to the case of unknown dynamics or opponents.
Bayesian Differential Privacy through Posterior Sampling
All our general results hold for arbitrary database metrics, including those for the common definition of differential privacy.
Cover Tree Bayesian Reinforcement Learning
This paper proposes an online tree-based Bayesian approach for reinforcement learning.
ABC Reinforcement Learning
This paper introduces a simple, general framework for likelihood-free Bayesian reinforcement learning, through Approximate Bayesian Computation (ABC).
Personalized News Recommendation with Context Trees
The profusion of online news articles makes it difficult to find interesting articles, a problem that can be assuaged by using a recommender system to bring the most relevant news stories to readers.
