Paul Barde

4 papers · 2020–2022 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (10) 📈 Trend Setter

Venues

ICLR (2) NeurIPS (2)

Top co-authors

Derek Nowrouzezahrai (4) Wonseok Jeon (2) Julien Roy (2) Chris Pal (2) Joelle Pineau (2) Christopher Pal (1) Félix Harvey (1) Pierre-yves Oudeyer (1) Tristan Karch (1) Thang Doan (1)

Research topics

Machine Learning (2) Reinforcement Learning (2) Learning Types (2) Methods (2) Artificial Intelligence (1) Core AI (1)

Keywords

policy regularization (2) multi-agent reinforcement learning (2) policy optimization (1) maximum entropy (1) inverse reinforcement learning (1) reward function (1) inductive bia (1) sparse reward (1) adversarial imitation learning (1) communication protocol (1) self-imitation learning (1) emergent communication (1) generator policy (1) architect-builder problem (1) interaction frame (1) imitation learning (1)

Papers

Learning to Guide and to be Guided in the Architect-Builder Problem ICLR 2022 Regularized Inverse Reinforcement Learning ICLR 2021 Adversarial Soft Advantage Fitting: Imitation Learning without Policy Optimization NeurIPS 2020 Promoting Coordination through Policy Regularization in Multi-Agent Deep Reinforcement Learning NeurIPS 2020