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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Adversarial Policies Beat Professional-Level Go AIs


Nov 01, 2022
Tony Tong Wang, Adam Gleave, Nora Belrose, Tom Tseng, Joseph Miller, Michael D Dennis, Yawen Duan, Viktor Pogrebniak, Sergey Levine, Stuart Russell

* 21 pages, 11 figures 

   Access Paper or Ask Questions

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

Calculus on MDPs: Potential Shaping as a Gradient


Aug 20, 2022
Erik Jenner, Herke van Hoof, Adam Gleave

* 17 pages, 6 figures 

   Access Paper or Ask Questions

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

Reducing Exploitability with Population Based Training


Aug 10, 2022
Pavel Czempin, Adam Gleave

* Presented at New Frontiers in Adversarial Machine Learning Workshop, ICML 2022 

   Access Paper or Ask Questions

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

Preprocessing Reward Functions for Interpretability


Mar 25, 2022
Erik Jenner, Adam Gleave

* Presented at the NeurIPS 2021 Cooperative AI workshop. Code available at https://github.com/HumanCompatibleAI/reward-preprocessing 

   Access Paper or Ask Questions

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

A Primer on Maximum Causal Entropy Inverse Reinforcement Learning


Mar 22, 2022
Adam Gleave, Sam Toyer

* 29 pages 

   Access Paper or Ask Questions

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

Invariance in Policy Optimisation and Partial Identifiability in Reward Learning


Mar 14, 2022
Joar Skalse, Matthew Farrugia-Roberts, Stuart Russell, Alessandro Abate, Adam Gleave

* 8 pages main paper, 24 pages total, 1 figure 

   Access Paper or Ask Questions

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

Uncertainty Estimation for Language Reward Models


Mar 14, 2022
Adam Gleave, Geoffrey Irving

* 8 pages main paper, 17 pages total 

   Access Paper or Ask Questions

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

Understanding Learned Reward Functions


Dec 10, 2020
Eric J. Michaud, Adam Gleave, Stuart Russell

* Presented at Deep RL Workshop, NeurIPS 2020 

   Access Paper or Ask Questions

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

DERAIL: Diagnostic Environments for Reward And Imitation Learning


Dec 02, 2020
Pedro Freire, Adam Gleave, Sam Toyer, Stuart Russell


   Access Paper or Ask Questions

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

Quantifying Differences in Reward Functions


Jun 24, 2020
Adam Gleave, Michael Dennis, Shane Legg, Stuart Russell, Jan Leike

* 8 pages main paper, 29 pages total 

   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
>>