• I will give my inaugural lecture at UZH: "Learning to Act: Reinforcement Learning and the Future of Decision-Making".
• Two papers accepted at EWRL 2024, see you in Toulouse!
• June 2024: Happy to share that I won an Hassler Research Grant for the project: "Unified Feedback Integration Framework for Reinforcement Learning". With this grant we will start developing an unified framework to work with different kinds of feedback in RL, such as preferences, rewards, and demonstrations.
• Thrilling 2024! Four papers accepted! "Provably learning nash policies in constrained markov potential games" at AAMAS 2024, "Exploiting causal graph priors with posterior sampling for reinforcement learning " at ICLR 2024, "Truly no-regret learning in constrained mdps" at ICML 2024, and "Stochastic bilevel optimization with lower-level contextual markov decision processes" at NeurIPS 2024.
• I ufficially started as tenure-track Assistant Professor at UZH!
• I am happy to be part of the ELLIS community.
• Our paper "On Imitation in Mean-field Games" has been accepted at NeurIPS 2023!
• I was invited as lecturer at the Mediterranean Machine Learning Summer School to talk about Deep Reinforcement Learning.
• I gave a talk on Reinforcement Learning and Multi-agent Learning at the New Frontiers in Learning, Control, and Dynamical Systems workshop at ICML 2023. See everyone in Hawaii!
• Four papers accepted at EWRL 2023!
• Designing and teaching a new course called Data Science and Machine Learning for the ETH-Ashesi Master program.
• Two papers accepted at NeurIPS 2022! "Active Exploration for Inverse Reinforcement Learning" and "Trust Region Policy Optimization with Optimal Transport Discrepancies: Duality and Algorithm for Continuous Actions".
• Our open problem "Do you pay for Privacy in Online learning?" has been selected at COLT 2022.
• Our paper "Active Exploration for Inverse Reinforcement Learning" has been accepted at the Adaptive Experimental Design and Active Learning in the Real World (ReALML) workshop at ICML 2022.
• Our paper "Learning in Markov Games: can we exploit a general-sum opponent?" has been accepted as oral (~4%) at UAI 2022.
show more
Designing and teaching a new course at ETH Zürich with AI Center postdocs in the spring term. The course is on various advanced topics including Inverse Reinforcement Learning.
I will visit the Simons Institute in January-February 2022 for the Learning and Games program.
Our paper "Learning in Non-Cooperative Configurable Markov Decision Process" has been accepted at NeurIPS 2021.
18.08.2021 I was selected to participate in the EECS RISING STARS 2021.
In August 2021 I joined the ETH AI Center as postdoctoral researcher.
In June 2021 I completed my Ph.D.!
Our paper "Provably Efficient Learning of Transferable Rewards" has been accepted at ICML 2021.
Our paper "Dealing with multiple experts and non-stationarity in inverse reinforcement learning: an application to real-life problems" has been published in the Machine Learning journal.
Our paper ‘‘Online Learning in Non-Cooperative Configurable Markov Decision Process’’ has been accepted at RLG 2021 workshop at AAAI.
Our paper ‘‘Newton Optimization on Helmholtz Decomposition for Continuous Games’’ has been accepted at AAAI2021.
Our paper ‘‘Handling Non-Stationary Experts in Inverse Reinforcement Learning: A Water System Control Case Study’’ has been accepted at Challenges of Real World Reinforcement Learning Workshop, and ‘‘Newton-based Policy Optimization for Games’’ has been accepted at CooperativeAI workshop.
Our paper ‘‘Controlled Text Generation with Adversarial Learning’’ has been accepted at INLG 2020.
Our paper "Inverse Reinforcement Learning from a Gradient-based Learner" has been accepted at NeurIPS 2020.
Our paper ‘‘Truly Batch Model-Free Inverse Reinforcement Learning about Multiple Intentions’’ has been accepted at AISTATS 2020.

Thanks Jon Barron for this nice template.