← Authors

Kamil Ciosek

13 papers · 2018–2022 · 6 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (6) 🐝 Cross-Pollinator (8) 🌈 Renaissance Researcher (5) πŸ—ΊοΈ Taxonomy Completionist (19) πŸ† Grand Slam πŸ‘‘ Triple Crown ⚑ Prolific Year (6) πŸ”₯ Unstoppable (5) πŸ“ˆ Trend Setter πŸ’Ž Century Club (13)

Conferences

NIPS (4) ICLR (3) ICML (2) JMLR (2) AAAI (1) AISTATS (1)

Top co-authors

Katja Hofmann (4) Sebastian Tschiatschek (3) Cheng Zhang (3) Shimon Whiteson (3) Ryota Tomioka (2) Sam Devlin (2) Quan Vuong (2) Matteo Turchetta (1) Vincent Fortuin (1) Richard Turner (1)

Keywords

reinforcement learning (4) information gain (2) continuous control (2) sample efficiency (1) policy optimization (1) domain generalization (1) robust optimization (1) fenchel duality (1) bayesian inference (1) information bottleneck (1) policy gradient (1) universal approximation (1) fourier analysis (1) robust reinforcement learning (1) discount factor (1) bayesian model (1) game theory (1) variance reduction (1) temporal-difference learning (1) metric learning (1)

Papers

Imitation Learning by Reinforcement Learning ICLR 2022
Estimating Ξ±-Rank by Maximizing Information Gain AAAI 2021
Regularized Policies are Reward Robust AISTATS 2021
Information Directed Reward Learning for Reinforcement Learning NIPS 2021
Robust Reinforcement Learning with Bayesian Optimisation and Quadrature JMLR 2020
Multi-task Batch Reinforcement Learning with Metric Learning NIPS 2020
Conservative Uncertainty Estimation By Fitting Prior Networks ICLR 2020
AMRL: Aggregated Memory For Reinforcement Learning ICLR 2020
Discount Factor as a Regularizer in Reinforcement Learning ICML 2020
Expected Policy Gradients for Reinforcement Learning JMLR 2020
Better Exploration with Optimistic Actor Critic NIPS 2019
Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck NIPS 2019
Fourier Policy Gradients ICML 2018