Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Towards Flexible Inference in Sequential Decision Problems via Bidirectional Transformers


Apr 28, 2022
Micah Carroll, Jessy Lin, Orr Paradise, Raluca Georgescu, Mingfei Sun, David Bignell, Stephanie Milani, Katja Hofmann, Matthew Hausknecht, Anca Dragan, Sam Devlin


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Monotonic Improvement Guarantees under Non-stationarity for Decentralized PPO


Jan 31, 2022
Mingfei Sun, Sam Devlin, Katja Hofmann, Shimon Whiteson


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

You May Not Need Ratio Clipping in PPO


Jan 31, 2022
Mingfei Sun, Vitaly Kurin, Guoqing Liu, Sam Devlin, Tao Qin, Katja Hofmann, Shimon Whiteson


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Deterministic and Discriminative Imitation (D2-Imitation): Revisiting Adversarial Imitation for Sample Efficiency


Dec 11, 2021
Mingfei Sun, Sam Devlin, Katja Hofmann, Shimon Whiteson

* AAAI 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Strategically Efficient Exploration in Competitive Multi-agent Reinforcement Learning


Jul 30, 2021
Robert Loftin, Aadirupa Saha, Sam Devlin, Katja Hofmann

* To Appear in Uncertainty in Artificial Intelligence (UAI) 2021. 10 figures, 14 pages 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Navigation Turing Test (NTT): Learning to Evaluate Human-Like Navigation


May 20, 2021
Sam Devlin, Raluca Georgescu, Ida Momennejad, Jaroslaw Rzepecki, Evelyn Zuniga, Gavin Costello, Guy Leroy, Ali Shaw, Katja Hofmann


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

The MineRL 2020 Competition on Sample Efficient Reinforcement Learning using Human Priors


Jan 26, 2021
William H. Guss, Mario Ynocente Castro, Sam Devlin, Brandon Houghton, Noboru Sean Kuno, Crissman Loomis, Stephanie Milani, Sharada Mohanty, Keisuke Nakata, Ruslan Salakhutdinov, John Schulman, Shinya Shiroshita, Nicholay Topin, Avinash Ummadisingu, Oriol Vinyals

* 37 pages, initial submission, accepted at NeurIPS. arXiv admin note: substantial text overlap with arXiv:1904.10079 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Evaluating the Robustness of Collaborative Agents


Jan 14, 2021
Paul Knott, Micah Carroll, Sam Devlin, Kamil Ciosek, Katja Hofmann, A. D. Dragan, Rohin Shah


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Deep Interactive Bayesian Reinforcement Learning via Meta-Learning


Jan 11, 2021
Luisa Zintgraf, Sam Devlin, Kamil Ciosek, Shimon Whiteson, Katja Hofmann


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Difference Rewards Policy Gradients


Dec 21, 2020
Jacopo Castellini, Sam Devlin, Frans A. Oliehoek, Rahul Savani

* This work as been accepted as an Extended Abstract in Proc. of the 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2021), U. Endriss, A. Now\'e, F. Dignum, A. Lomuscio (eds.), May 3-7 2021, Online 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
>>