research
∙
10/31/2022
Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information
Learning to control an agent from data collected offline in a rich pixel...
share
research
∙
10/05/2022
Tractable Optimality in Episodic Latent MABs
We consider a multi-armed bandit problem with M latent contexts, where a...
research
∙
10/05/2022
Reward-Mixing MDPs with a Few Latent Contexts are Learnable
We consider episodic reinforcement learning in reward-mixing Markov deci...
research
∙
07/17/2022
Guaranteed Discovery of Controllable Latent States with Multi-Step Inverse Models
A person walking along a city street who tries to model all aspects of t...
research
∙
06/09/2022
Sample-Efficient Reinforcement Learning in the Presence of Exogenous Information
In real-world reinforcement learning applications the learner's observat...
research
∙
02/08/2022
Provable Reinforcement Learning with a Short-Term Memory
Real-world sequential decision making problems commonly involve partial ...
research
∙
01/30/2022
Coordinated Attacks against Contextual Bandits: Fundamental Limits and Defense Mechanisms
Motivated by online recommendation systems, we propose the problem of fi...
research
∙
10/17/2021
Provable RL with Exogenous Distractors via Multistep Inverse Dynamics
Many real-world applications of reinforcement learning (RL) require the ...
research
∙
10/12/2021
Sparsity in Partially Controllable Linear Systems
A fundamental concept in control theory is that of controllability, wher...
research
∙
10/12/2021
Dare not to Ask: Problem-Dependent Guarantees for Budgeted Bandits
We consider a stochastic multi-armed bandit setting where feedback is li...
research
∙
10/07/2021
Reinforcement Learning in Reward-Mixing MDPs
Learning a near optimal policy in a partially observable system remains ...
research
∙
03/24/2021
Minimax Regret for Stochastic Shortest Path
We study the Stochastic Shortest Path (SSP) problem in which an agent ha...
research
∙
02/09/2021
RL for Latent MDPs: Regret Guarantees and a Lower Bound
In this work, we consider the regret minimization problem for reinforcem...
research
∙
08/13/2020
Reinforcement Learning with Trajectory Feedback
The computational model of reinforcement learning is based upon the abil...
research
∙
06/11/2020
Bandits with Partially Observable Offline Data
We study linear contextual bandits with access to a large, partially obs...
research
∙
05/20/2020
Mirror Descent Policy Optimization
We propose deep Reinforcement Learning (RL) algorithms inspired by mirro...
research
∙
03/04/2020
Exploration-Exploitation in Constrained MDPs
In many sequential decision-making problems, the goal is to optimize a u...
research
∙
02/19/2020
Optimistic Policy Optimization with Bandit Feedback
Policy optimization methods are one of the most widely used classes of R...
research
∙
10/07/2019
Multi-step Greedy Policies in Model-Free Deep Reinforcement Learning
Multi-step greedy policies have been extensively used in model-based Rei...
research
∙
09/10/2019
Multi-Step Greedy and Approximate Real Time Dynamic Programming
Real Time Dynamic Programming (RTDP) is a well-known Dynamic Programming...
research
∙
09/06/2019
Adaptive Trust Region Policy Optimization: Global Convergence and Faster Rates for Regularized MDPs
Trust region policy optimization (TRPO) is a popular and empirically suc...
research
∙
05/27/2019
Tight Regret Bounds for Model-Based Reinforcement Learning with Greedy Policies
State-of-the-art efficient model-based Reinforcement Learning (RL) algor...
research
∙
01/26/2019
Action Robust Reinforcement Learning and Applications in Continuous Control
A policy is said to be robust if it maximizes the reward while consideri...
research
∙
12/13/2018
Revisiting Exploration-Conscious Reinforcement Learning
The objective of Reinforcement Learning is to learn an optimal policy by...
research
∙
09/06/2018
How to Combine Tree-Search Methods in Reinforcement Learning
Finite-horizon lookahead policies are abundantly used in Reinforcement L...
research
∙
05/21/2018
Multiple-Step Greedy Policies in Online and Approximate Reinforcement Learning
Multiple-step lookahead policies have demonstrated high empirical compet...
research
∙
02/10/2018