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

Add to Chrome

Add to Firefox

Picture for Adam Gleave

Adam Gleave

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

Figure 1 for Adversarial Policies Beat Professional-Level Go AIs

Figure 2 for Adversarial Policies Beat Professional-Level Go AIs

Figure 3 for Adversarial Policies Beat Professional-Level Go AIs

Figure 4 for Adversarial Policies Beat Professional-Level Go AIs

* 21 pages, 11 figures

Access Paper or Ask Questions

Calculus on MDPs: Potential Shaping as a Gradient

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

Figure 1 for Calculus on MDPs: Potential Shaping as a Gradient

Figure 2 for Calculus on MDPs: Potential Shaping as a Gradient

Figure 3 for Calculus on MDPs: Potential Shaping as a Gradient

Figure 4 for Calculus on MDPs: Potential Shaping as a Gradient

* 17 pages, 6 figures

Access Paper or Ask Questions

Reducing Exploitability with Population Based Training

Aug 10, 2022
Pavel Czempin, Adam Gleave

Figure 1 for Reducing Exploitability with Population Based Training

Figure 2 for Reducing Exploitability with Population Based Training

Figure 3 for Reducing Exploitability with Population Based Training

Figure 4 for Reducing Exploitability with Population Based Training

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

Access Paper or Ask Questions

Preprocessing Reward Functions for Interpretability

Mar 25, 2022
Erik Jenner, Adam Gleave

Figure 1 for Preprocessing Reward Functions for Interpretability

Figure 2 for Preprocessing Reward Functions for Interpretability

Figure 3 for Preprocessing Reward Functions for Interpretability

Figure 4 for Preprocessing Reward Functions for Interpretability

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

Access Paper or Ask Questions

A Primer on Maximum Causal Entropy Inverse Reinforcement Learning

Mar 22, 2022
Adam Gleave, Sam Toyer

Figure 1 for A Primer on Maximum Causal Entropy Inverse Reinforcement Learning

* 29 pages

Access Paper or Ask Questions

Invariance in Policy Optimisation and Partial Identifiability in Reward Learning

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

Figure 1 for Invariance in Policy Optimisation and Partial Identifiability in Reward Learning

Figure 2 for Invariance in Policy Optimisation and Partial Identifiability in Reward Learning

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

Access Paper or Ask Questions

Uncertainty Estimation for Language Reward Models

Mar 14, 2022
Adam Gleave, Geoffrey Irving

Figure 1 for Uncertainty Estimation for Language Reward Models

Figure 2 for Uncertainty Estimation for Language Reward Models

Figure 3 for Uncertainty Estimation for Language Reward Models

Figure 4 for Uncertainty Estimation for Language Reward Models

* 8 pages main paper, 17 pages total

Access Paper or Ask Questions

Understanding Learned Reward Functions

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

Figure 1 for Understanding Learned Reward Functions

Figure 2 for Understanding Learned Reward Functions

Figure 3 for Understanding Learned Reward Functions

Figure 4 for Understanding Learned Reward Functions

* Presented at Deep RL Workshop, NeurIPS 2020

Access Paper or Ask Questions

DERAIL: Diagnostic Environments for Reward And Imitation Learning

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

Figure 1 for DERAIL: Diagnostic Environments for Reward And Imitation Learning

Figure 2 for DERAIL: Diagnostic Environments for Reward And Imitation Learning

Figure 3 for DERAIL: Diagnostic Environments for Reward And Imitation Learning

Figure 4 for DERAIL: Diagnostic Environments for Reward And Imitation Learning

Access Paper or Ask Questions

Quantifying Differences in Reward Functions

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

Figure 1 for Quantifying Differences in Reward Functions

Figure 2 for Quantifying Differences in Reward Functions

Figure 3 for Quantifying Differences in Reward Functions

Figure 4 for Quantifying Differences in Reward Functions

* 8 pages main paper, 29 pages total

Access Paper or Ask Questions