Csaba Szepesvári
5 papers in the PaperMetrix corpus
Papers by this author
-
Rigorous Agent Evaluation: An Adversarial Approach to Uncover Catastrophic Failures
2018 · arXiv (Cornell University)
This paper addresses the problem of evaluating learning systems in safety critical domains such as autonomous driving, where failures can have catastrophic consequences. We focus on two problems: searching for scenarios when learned agents fail …
-
Autonomous exploration for navigating in non-stationary CMPs
2019 · arXiv (Cornell University)
We consider a setting in which the objective is to learn to navigate in a controlled Markov process (CMP) where transition probabilities may abruptly change. For this setting, we propose a performance measure called exploration …
-
Near-Optimal Sample Complexity Bounds for Constrained MDPs
2022 · arXiv (Cornell University)
In contrast to the advances in characterizing the sample complexity for solving Markov decision processes (MDPs), the optimal statistical complexity for solving constrained MDPs (CMDPs) remains unknown. We resolve this question by providing minimax upper …
-
The Curse of Passive Data Collection in Batch Reinforcement Learning
2021 · arXiv (Cornell University)
In high stake applications, active experimentation may be considered too risky and thus data are often collected passively. While in simple cases, such as in bandits, passive and active data collection are similarly effective, the …
-
Trajectory Data Suffices for Statistically Efficient Learning in Offline RL with Linear $q^π$-Realizability and Concentrability
2024 · arXiv (Cornell University)
We consider offline reinforcement learning (RL) in $H$-horizon Markov decision processes (MDPs) under the linear $q^π$-realizability assumption, where the action-value function of every policy is linear with respect to a given $d$-dimensional feature function. The …