Rati Devidze

რატი დევიძე*

Rati Devidze

Email : "r.devidze" at "gmail.com" or "rdevidze" at "mpi-sws.org"

[Linkedin]  [Github]  [Google Scholar]

Hello!

My name is Rati Devidze and I am a PhD student in Machine Teaching Group at MPI-SWS , Saarbrücken, Germany.

My Interests

I like algorithmic machine learning and my interests are:

-(Inverse)Reinforcement learning

-Machine teaching

-Machine learning

More information

For more information about me, please see my [ CV ].

Publications:

Exploration-Guided Reward Shaping for Reinforcement Learning under Sparse Rewards
R. Devidze, P. Kamalaruban, A. Singla
In Proc. of the 36th Conference on Neural Information Processing Systems (NeurIPS'22), 2022

Explicable Reward Design for Reinforcement Learning Agents
R. Devidze, G. Radanovic, P. Kamalaruban, A. Singla
In Proc. of the 35th Conference on Neural Information Processing Systems (NeurIPS'21), 2021

Policy Teaching in Reinforcement Learning via Environment Poisoning Attacks
A. Rakhsha, G. Radanovic, R. Devidze, X. Zhu, A. Singla
Journal of Machine Learning Research (JMLR), 2021

Understanding the Power and Limitations of Teaching with Imperfect Knowledge
R. Devidze*, F. Mansouri*, L. Haug, Y. Chen, A. Singla
( * Authors have contributed equally to this work)
In Proc. of the 29th International Joint Conference on Artificial Intelligence (IJCAI'20), 2020

Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learning
A. Rakhsha, G. Radanovic, R. Devidze, X. Zhu, A. Singla
In Proc. of the 37th International Conference on Machine Learning (ICML'20), 2020

Environment Shaping in Reinforcement Learning using State Abstraction
P. Kamalaruban, R. Devidze, V. Cevher, A. Singla
In Challenges of Real World Reinforcement Learning Workshop at NeurIPS'20, 2020

Learner-aware Teaching: Inverse Reinforcement Learning with Preferences and Constraints
S. Tschiatschek*, A. Ghosh*, L. Haug*, R. Devidze, A. Singla
( * Authors have contributed equally to this work)
In Proc. of the 33rd Conference on Neural Information Processing Systems (NeurIPS'19), 2019

Interactive Teaching Algorithms for Inverse Reinforcement Learning
P. Kamalaruban*, R. Devidze *, V. Cevher, A. Singla
( * Authors have contributed equally to this work)
In Proc. of the 28th International Joint Conference on Artificial Intelligence (IJCAI'19), 2019

Learning to Collaborate in Markov Decision Processes
G. Radanovic, R. Devidze, D. Parkes, A. Singla
In Proc. of the 36th International Conference on Machine Learning (ICML'19), 2019

Assisted Inverse Reinforcement Learning
P. Kamalaruban, R. Devidze, T. Yeo, T. Mittal, V. Cevher, A. Singla
In Learning by Instruction Workshop at NeurIPS'18, 2018