R. Devidze

发表

Assisted Inverse Reinforcement Learning

Parameswaran Kamalaruban, Adish Singla, Trisha Mittal, 2018 .

Explicable Reward Design for Reinforcement Learning Agents

A. Singla, Parameswaran Kamalaruban, Goran Radanovic, 2021, NeurIPS.

Understanding the Power and Limitations of Teaching with Imperfect Knowledge

Yuxin Chen, Adish Singla, Rati Devidze, 2020, IJCAI.

L G ] 2 0 Ju n 20 19 Learning to Collaborate in Markov Decision Processes

D. Parkes, A. Singla, Goran Radanovic, 2019 .

Curriculum Design for Teaching via Demonstrations: Theory and Applications pdf

Parameswaran Kamalaruban, Gaurav Yengera, Adish Singla, 2021, NeurIPS.

Policy Teaching in Reinforcement Learning via Environment Poisoning Attacks pdf

Xiaojin Zhu, Adish Singla, Goran Radanovic, 2020, J. Mach. Learn. Res..

Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learning pdf

Xiaojin Zhu, Adish Singla, Goran Radanovic, 2020, ICML.

Potential-based reward shaping for learning to play text-based adventure games

R. Devidze, Weichen Li, Sophie Fellenz, 2023, ArXiv.

Interactive Teaching Algorithms for Inverse Reinforcement Learning

Volkan Cevher, Parameswaran Kamalaruban, Adish Singla, 2019, IJCAI.

Learning to Collaborate in Markov Decision Processes

D. Parkes, A. Singla, Goran Radanovic, 2019, ICML.

Learner-aware Teaching: Inverse Reinforcement Learning with Preferences and Constraints

A. Singla, Sebastian Tschiatschek, R. Devidze, 2019, NeurIPS.

Exploration-Guided Reward Shaping for Reinforcement Learning under Sparse Rewards

A. Singla, Parameswaran Kamalaruban, R. Devidze, 2022, NeurIPS.

Environment Shaping in Reinforcement Learning using State Abstraction pdf

Parameswaran Kamalaruban, Adish Singla, Rati Devidze, 2020, ArXiv.

Understanding the Power and Limitations of Teaching with Imperfect Knowledge pdf

Adish Singla, Rati Devidze, Yuxin Chen, 2020, IJCAI.