Alert button
Picture for Nicolas Porcel

Nicolas Porcel

Alert button

Open-Ended Learning Leads to Generally Capable Agents

Jul 31, 2021
Open Ended Learning Team, Adam Stooke, Anuj Mahajan, Catarina Barros, Charlie Deck, Jakob Bauer, Jakub Sygnowski, Maja Trebacz, Max Jaderberg, Michael Mathieu, Nat McAleese, Nathalie Bradley-Schmieg, Nathaniel Wong, Nicolas Porcel, Roberta Raileanu, Steph Hughes-Fitt, Valentin Dalibard, Wojciech Marian Czarnecki

Figure 1 for Open-Ended Learning Leads to Generally Capable Agents
Figure 2 for Open-Ended Learning Leads to Generally Capable Agents
Figure 3 for Open-Ended Learning Leads to Generally Capable Agents
Figure 4 for Open-Ended Learning Leads to Generally Capable Agents
Viaarxiv icon

Alchemy: A structured task distribution for meta-reinforcement learning

Feb 04, 2021
Jane X. Wang, Michael King, Nicolas Porcel, Zeb Kurth-Nelson, Tina Zhu, Charlie Deck, Peter Choy, Mary Cassin, Malcolm Reynolds, Francis Song, Gavin Buttimore, David P. Reichert, Neil Rabinowitz, Loic Matthey, Demis Hassabis, Alexander Lerchner, Matthew Botvinick

Figure 1 for Alchemy: A structured task distribution for meta-reinforcement learning
Figure 2 for Alchemy: A structured task distribution for meta-reinforcement learning
Figure 3 for Alchemy: A structured task distribution for meta-reinforcement learning
Figure 4 for Alchemy: A structured task distribution for meta-reinforcement learning
Viaarxiv icon

Learning to Play No-Press Diplomacy with Best Response Policy Iteration

Jun 17, 2020
Thomas Anthony, Tom Eccles, Andrea Tacchetti, János Kramár, Ian Gemp, Thomas C. Hudson, Nicolas Porcel, Marc Lanctot, Julien Pérolat, Richard Everett, Satinder Singh, Thore Graepel, Yoram Bachrach

Figure 1 for Learning to Play No-Press Diplomacy with Best Response Policy Iteration
Figure 2 for Learning to Play No-Press Diplomacy with Best Response Policy Iteration
Figure 3 for Learning to Play No-Press Diplomacy with Best Response Policy Iteration
Figure 4 for Learning to Play No-Press Diplomacy with Best Response Policy Iteration
Viaarxiv icon