40.2k citations
- Max Planck SocietyDE68 papers
- University of OxfordGB25 papers
- Centre National de la Recherche ScientifiqueFR24 papers
- Saarland UniversityDE17 papers
- University of CambridgeGB12 papers
- ETH ZurichCH11 papers
- IMDEA Software InstituteES10 papers
- Indian Institute of Technology KharagpurIN10 papers
- University of California, Los AngelesUS10 papers
- Max Planck Institute for InformaticsDE9 papers
- National University of SingaporeSG9 papers
- Newcastle UniversityGB9 papers
13 papers · 2 filters
Policy Teaching in Reinforcement Learning via Environment Poisoning Attacks
Amin Rakhsha, Goran Radanovic, Rati Devidze +2
We study a security threat to reinforcement learning where an attacker poisons the learning environment to force the agent into executing a target policy chosen by the attacker. As…
Preference-Based Batch and Sequential Teaching
Farnam Mansouri, Yuxin Chen, Ara Vartanian +2
Algorithmic machine teaching studies the interaction between a teacher and a learner where the teacher selects labeled examples aiming at teaching a target hypothesis. In a quest t…
The Teaching Dimension of Kernel Perceptron
Akash Kumar, Hanqi Zhang, Adish Singla +1
Algorithmic machine teaching has been studied under the linear setting where exact teaching is possible. However, little is known for teaching nonlinear learners. Here, we establis…
Property-Directed Verification of Recurrent Neural Networks
Igor Khmelnitsky, Daniel Neider, Rajarshi Roy +6
This paper presents a property-directed approach to verifying recurrent neural networks (RNNs). To this end, we learn a deterministic finite automaton as a surrogate model from a g…
Task-agnostic Exploration in Reinforcement Learning
Xuezhou Zhang, Yuzhe ma, Adish Singla
Efficient exploration is one of the main challenges in reinforcement learning (RL). Most existing sample-efficient algorithms assume the existence of a single reward function durin…
Active Finite Reward Automaton Inference and Reinforcement Learning Using Queries and Counterexamples
Zhe Xu, Bo Wu, Aditya Ojha +2
Despite the fact that deep reinforcement learning (RL) has surpassed human-level performances in various tasks, it still has several fundamental challenges. First, most RL methods…