Preprocessing Reward Functions for Interpretability von Jenner, Erik, Gleave, Adam

Volltext bestellen

Steerable Partial Differential Operators for Equivariant Neural Networks von Jenner, Erik, Weiler, Maurice

Volltext bestellen

Diffusion On Syntax Trees For Program Synthesis von Kapur, Shreyas, Jenner, Erik, Russell, Stuart

Volltext bestellen

Calculus on MDPs: Potential Shaping as a Gradient von Jenner, Erik, van Hoof, Herke, Gleave, Adam

Volltext bestellen

Steerable Partial Differential Operators for Equivariant Neural Networks von Jenner, Erik, Weiler, Maurice

Volltext

Preprocessing Reward Functions for Interpretability von Jenner, Erik, Gleave, Adam

Volltext

Evidence of Learned Look-Ahead in a Chess-Playing Neural Network von Jenner, Erik, Kapur, Shreyas, Georgiev, Vasil, Allen, Cameron, Emmons, Scott, Russell, Stuart

Volltext bestellen

When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback von Lang, Leon, Foote, Davis, Russell, Stuart, Dragan, Anca, Jenner, Erik, Emmons, Scott

Volltext bestellen

Diffusion On Syntax Trees For Program Synthesis von Kapur, Shreyas, Jenner, Erik, Russell, Stuart

Volltext

STARC: A General Framework For Quantifying Differences Between Reward Functions von Skalse, Joar, Farnik, Lucy, Motwani, Sumeet Ramesh, Jenner, Erik, Gleave, Adam, Abate, Alessandro

Volltext bestellen

Extensions of Karger's Algorithm: Why They Fail in Theory and How They Are Useful in Practice von Jenner, Erik, Sanmartín, Enrique Fita, Hamprecht, Fred A

Volltext bestellen

Calculus on MDPs: Potential Shaping as a Gradient von Jenner, Erik, Herke van Hoof, Gleave, Adam

Volltext

imitation: Clean Imitation Learning Implementations von Gleave, Adam, Taufeeque, Mohammad, Rocamonde, Juan, Jenner, Erik, Wang, Steven H, Toyer, Sam, Ernestus, Maximilian, Belrose, Nora, Emmons, Scott, Russell, Stuart

Volltext bestellen

When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback von Lang, Leon, Foote, Davis, Russell, Stuart, Dragan, Anca, Jenner, Erik, Emmons, Scott

Volltext

Evidence of Learned Look-Ahead in a Chess-Playing Neural Network von Jenner, Erik, Kapur, Shreyas, Georgiev, Vasil, Cameron, Allen, Emmons, Scott, Russell, Stuart

Volltext

STARC: A General Framework For Quantifying Differences Between Reward Functions von Skalse, Joar, Farnik, Lucy, Sumeet Ramesh Motwani, Jenner, Erik, Gleave, Adam, Abate, Alessandro

Volltext

Foundational Challenges in Assuring Alignment and Safety of Large Language Models von Anwar, Usman, Saparov, Abulhair, Rando, Javier, Paleka, Daniel, Turpin, Miles, Hase, Peter, Lubana, Ekdeep Singh, Jenner, Erik, Casper, Stephen, Sourbut, Oliver, Edelman, Benjamin L, Zhang, Zhaowei, Günther, Mario, Korinek, Anton, Hernandez-Orallo, Jose, Hammond, Lewis, Bigelow, Eric, Pan, Alexander, Langosco, Lauro, Korbak, Tomasz, Zhang, Heidi, Zhong, Ruiqi, hÉigeartaigh, Seán Ó, Recchia, Gabriel, Corsi, Giulio, Chan, Alan, Anderljung, Markus, Edwards, Lilian, Petrov, Aleksandar, de Witt, Christian Schroeder, Motwan, Sumeet Ramesh, Bengio, Yoshua, Chen, Danqi, Torr, Philip H. S, Albanie, Samuel, Maharaj, Tegan, Foerster, Jakob, Tramer, Florian, He, He, Kasirzadeh, Atoosa, Choi, Yejin, Krueger, David

Volltext bestellen

Extensions of Karger's Algorithm: Why They Fail in Theory and How They Are Useful in Practice von Jenner, Erik, Enrique Fita Sanmartín, Hamprecht, Fred A

Volltext

imitation: Clean Imitation Learning Implementations von Gleave, Adam, Taufeeque, Mohammad, Rocamonde, Juan, Jenner, Erik, Wang, Steven H, Toyer, Sam, Ernestus, Maximilian, Belrose, Nora, Emmons, Scott, Russell, Stuart

Volltext

Foundational Challenges in Assuring Alignment and Safety of Large Language Models von Usman Anwar, Saparov, Abulhair, Rando, Javier, Paleka, Daniel, Turpin, Miles, Hase, Peter, Ekdeep Singh Lubana, Jenner, Erik, Casper, Stephen, Sourbut, Oliver, Edelman, Benjamin L, Zhang, Zhaowei, Günther, Mario, Korinek, Anton, Hernandez-Orallo, Jose, Hammond, Lewis, Bigelow, Eric, Pan, Alexander, Langosco, Lauro, Korbak, Tomasz, Zhang, Heidi, Zhong, Ruiqi, Seán Ó hÉigeartaigh, Recchia, Gabriel, Corsi, Giulio, Chan, Alan, Anderljung, Markus, Edwards, Lilian, Bengio, Yoshua, Chen, Danqi, Albanie, Samuel, Maharaj, Tegan, Foerster, Jakob, Tramer, Florian, He, He, Kasirzadeh, Atoosa, Choi, Yejin, Krueger, David

Volltext