- Dimitrakakis, Christos

###### Options

# Dimitrakakis, Christos

Nom

Dimitrakakis, Christos

Affiliation principale

Fonction

Professor

Email

christos.dimitrakakis@unine.ch

Identifiants

## Résultat de la recherche

46 Résultats Retour aux résultats

### Filtres

##### Auteur

##### Éditeur

##### Institution

##### Sujet

##### Fichier(s) présent(s)

##### Type

### Paramètres

Trier par

Résultats par page

Voici les éléments 1 - 10 sur 46

- PublicationAccès libreReinforcement Learning in the Wild with Maximum Likelihood-based Model Transfer(2023)
;Hannes Eriksson ;Debabrota Basu ;Tommy Tram ;Mina AlibeigiMontrer plus In this paper, we study the problem of transferring the available Markov Decision Process (MDP) models to learn and plan efficiently in an unknown but similar MDP. We refer to it as \textit{Model Transfer Reinforcement Learning (MTRL)} problem. First, we formulate MTRL for discrete MDPs and Linear Quadratic Regulators (LQRs) with continuous state actions. Then, we propose a generic two-stage algorithm, MLEMTRL, to address the MTRL problem in discrete and continuous settings. In the first stage, MLEMTRL uses a \textit{constrained Maximum Likelihood Estimation (MLE)}-based approach to estimate the target MDP model using a set of known MDP models. In the second stage, using the estimated target MDP model, MLEMTRL deploys a model-based planning algorithm appropriate for the MDP class. Theoretically, we prove worst-case regret bounds for MLEMTRL both in realisable and non-realisable settings. We empirically demonstrate that MLEMTRL allows faster learning in new MDPs than learning from scratch and achieves near-optimal performance depending on the similarity of the available MDPs and the target MDP.Montrer plus - PublicationAccès libreMinimax-Bayes Reinforcement Learning(PMLR, 2023)
;Thomas Kleine Buening; ;Hannes Eriksson ;Divya GroverEmilio JorgeMontrer plus 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. One idea is to employ a worst-case prior. However, this is not as easy to specify in sequential decision making as in simple statistical estimation problems. This paper studies (sometimes approximate) minimax-Bayes solutions for various reinforcement learning problems to gain insights into the properties of the corresponding priors and policies. We find that while the worst-case prior depends on the setting, the corresponding minimax policies are more robust than those that assume a standard (i.e. uniform) prior.Montrer plus - PublicationAccès libreRisk-Sensitive Bayesian Games for Multi-Agent Reinforcement Learning under Policy Uncertainty(2022-03-18T16:40:30Z)
;Hannes Eriksson ;Debabrota Basu ;Mina AlibeigiMontrer plus In stochastic games with incomplete information, the uncertainty is evoked by the lack of knowledge about a player's own and the other players' types, i.e. the utility function and the policy space, and also the inherent stochasticity of different players' interactions. 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. In this work, we instead focus on the risk associated with the \textit{uncertainty over types}. We contrast this with the multi-agent reinforcement learning framework where the other agents have fixed stationary policies and investigate risk-sensitiveness due to the uncertainty about the other agents' adaptive policies. We propose risk-sensitive versions of existing algorithms proposed for risk-neutral stochastic games, such as Iterated Best Response (IBR), Fictitious Play (FP) and a general multi-objective gradient approach using dual ascent (DAPG). Our experimental analysis shows that risk-sensitive DAPG performs better than competing algorithms for both social welfare and general-sum stochastic games.Montrer plus - PublicationAccès libreEnvironment Design for Inverse Reinforcement Learning(2022)
;Thomas Kleine BueningMontrer plus The task of learning a reward function from expert demonstrations suffers from high sample complexity as well as inherent limitations to what can be learned from demonstrations in a given environment. As the samples used for reward learning require human input, which is generally expensive, much effort has been dedicated towards designing more sample-efficient algorithms. Moreover, even with abundant data, current methods can still fail to learn insightful reward functions that are robust to minor changes in the environment dynamics. We approach these challenges differently than prior work by improving the sample-efficiency as well as the robustness of learned rewards through adaptively designing a sequence of demonstration environments for the expert to act in. We formalise a framework for this environment design process in which learner and expert repeatedly interact, and construct algorithms that actively seek information about the rewards by carefully curating environments for the human to demonstrate the task in.Montrer plus - PublicationAccès libreInteractive Inverse Reinforcement Learning for Cooperative Games(2022)
;Thomas Kleine Büning ;Anne-Marie GeorgeMontrer plus We study the problem of designing autonomous agents that can learn to cooperate effectively with a potentially suboptimal partner while having no access to the joint reward function. This problem is modeled as a cooperative episodic two-agent Markov decision process. We assume control over only the first of the two agents in a Stackelberg formulation of the game, where the second agent is acting so as to maximise expected utility given the first agent’s policy. 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? We analyse how knowledge about the reward function can be gained in this interactive two-agent scenario. We show that when the learning agent’s policies have a significant effect on the transition function, the reward function can be learned efficiently.Montrer plus - PublicationAccès libreSimulating University Application Data for Fair Matchings(2022)
;Meirav Segal ;Anne-Marie GeorgeMontrer plus - PublicationAccès libreHigh-dimensional near-optimal experiment design for drug discovery via Bayesian sparse sampling(2021-04-23T22:43:16Z)
;Hannes Eriksson; Lars CarlssonMontrer plus We study the problem of performing automated experiment design for drug screening through Bayesian inference and optimisation. In particular, we compare and contrast the behaviour of linear-Gaussian models and Gaussian processes, when used in conjunction with upper confidence bound algorithms, Thompson sampling, or bounded horizon tree search. We show that non-myopic sophisticated exploration techniques using sparse tree search have a distinct advantage over methods such as Thompson sampling or upper confidence bounds in this setting. We demonstrate the significant superiority of the approach over existing and synthetic datasets of drug toxicity.Montrer plus - PublicationAccès libreAdaptive Belief Discretization for POMDP Planning(2021-04-15T07:04:32Z)
;Divya GroverMontrer plus Partially Observable Markov Decision Processes (POMDP) is a widely used model to represent the interaction of an environment and an agent, under state uncertainty. Since the agent does not observe the environment state, its uncertainty is typically represented through a probabilistic belief. While the set of possible beliefs is infinite, making exact planning intractable, the belief space's complexity (and hence planning complexity) is characterized by its covering number. Many POMDP solvers uniformly discretize the belief space and give the planning error in terms of the (typically unknown) covering number. We instead propose an adaptive belief discretization scheme, and give its associated planning error. We furthermore characterize the covering number with respect to the POMDP parameters. This allows us to specify the exact memory requirements on the planner, needed to bound the value function error. We then propose a novel, computationally efficient solver using this scheme. We demonstrate that our algorithm is highly competitive with the state of the art in a variety of scenarios.Montrer plus - PublicationAccès libreOn Meritocracy in Optimal Set Selection(2021-02-23T20:36:36Z)
;Thomas Kleine Buening ;Meirav Segal ;Debabrota Basu; Anne-Marie GeorgeMontrer plus Typically, merit is defined with respect to some intrinsic measure of worth. We instead consider a setting where an individual's worth is \emph{relative}: when a Decision Maker (DM) selects a set of individuals from a population to maximise expected utility, it is natural to consider the \emph{Expected Marginal Contribution} (EMC) of each person to the utility. We show that this notion satisfies an axiomatic definition of fairness for this setting. We also show that for certain policy structures, this notion of fairness is aligned with maximising expected utility, while for linear utility functions it is identical to the Shapley value. However, for certain natural policies, such as those that select individuals with a specific set of attributes (e.g. high enough test scores for college admissions), there is a trade-off between meritocracy and utility maximisation. We analyse the effect of constraints on the policy on both utility and fairness in extensive experiments based on college admissions and outcomes in Norwegian universities.Montrer plus - PublicationAccès libreSENTINEL: Taming Uncertainty with Ensemble-based Distributional Reinforcement Learning(2021-02-22T14:45:39Z)
;Hannes Eriksson ;Debabrota Basu ;Mina AlibeigiMontrer plus In this paper, we consider risk-sensitive sequential decision-making in Reinforcement Learning (RL). Our contributions are two-fold. First, we introduce a novel and coherent quantification of risk, namely composite risk, which quantifies the joint effect of aleatory and epistemic risk during the learning process. Existing works considered either aleatory or epistemic risk individually, or as an additive combination. We prove that the additive formulation is a particular case of the composite risk when the epistemic risk measure is replaced with expectation. Thus, the composite risk is more sensitive to both aleatory and epistemic uncertainty than the individual and additive formulations. We also propose an algorithm, SENTINEL-K, based on ensemble bootstrapping and distributional RL for representing epistemic and aleatory uncertainty respectively. The ensemble of K learners uses Follow The Regularised Leader (FTRL) to aggregate the return distributions and obtain the composite risk. We experimentally verify that SENTINEL-K estimates the return distribution better, and while used with composite risk estimates, demonstrates higher risk-sensitive performance than state-of-the-art risk-sensitive and distributional RL algorithms.Montrer plus