Recent Papers

A Simple Recipe to Meta-Learn Forward and Backward Transfer

A Simple Recipe to Meta-Learn Forward and Backward Transfer
Edoardo Cetin, Antonio Carta, Oya Celiktutan.
International Conference on Computer Vision . ICCV 2023.
[Site][Code]

Hyperbolic Deep Reinforcement Learning

Hyperbolic Deep Reinforcement Learning
Edoardo Cetin, Benjamin Chamberlain, Michael Bronstein, Jonathan J Hunt.
International Conference on Learning Representations (notable-top-25% paper). ICLR 2023.
[arXiv][Site][Code]

Learning Pessimism for Robust and Efficient Off-Policy Reinforcement Learning

Learning Pessimism for Reinforcement Learning
Edoardo Cetin, Oya Celiktutan.
AAAI Conference on Artificial Intelligence (oral presentation). AAAI 2023.
[arXiv]

Policy Gradient With Serial Markov Chain Reasoning

Policy Gradient With Serial Markov Chain Reasoning
Edoardo Cetin, Oya Celiktutan.
Conference on Neural Information Processing Systems. NeurIPS 2022.
[arXiv][Site]

Stabilizing Off-Policy Deep Reinforcement Learning from Pixels

Stabilizing Off-Policy Deep Reinforcement Learning from Pixels
Edoardo Cetin, Philip Ball, Steve Roberts, Oya Celiktutan.
International Conference on Machine Learning. ICML 2022.
[arXiv][Site][Code]

Learning Routines for Effective Off-Policy Reinforcement Learning

Learning Routines for Effective Off-Policy Reinforcement Learning
Edoardo Cetin, Oya Celiktutan.
International Conference on Machine Learning. ICML 2021.
[arXiv][Site][Code]

Domain-Robust Visual Imitation Learning with Mutual Information Constraints

Domain-Robust Visual Imitation Learning with Mutual Information Constraints
Edoardo Cetin, Oya Celiktutan.
International Conference on Learning Representations. ICLR 2021.
[arXiv][Site][Code]