Miljan Martic | DeepAI

AI Chat

Featured Co-authors

Pushmeet Kohli
93 publications
Shane Legg
41 publications
David Krueger
31 publications
Pedro A. Ortega
30 publications
Dario Amodei
27 publications
Jan Leike
27 publications
Tom Everitt
25 publications
Matteo Hessel
25 publications
Laurent Orseau
22 publications
Jordi Grau-Moya
19 publications
Tim Genewein
19 publications

∙ 03/05/2021

Causal Analysis of Agent Behavior for AI Safety

As machine learning systems become more powerful they also become increa...

26 Grégoire Delétang, et al. ∙

∙ 10/23/2020

Algorithms for Causal Reasoning in Probability Trees

Probability trees are one of the simplest models of causal generative pr...

2 Tim Genewein, et al. ∙

∙ 10/21/2020

Meta-trained agents implement Bayes-optimal agents

Memory-based meta-learning is a powerful technique to build agents that ...

8 Vladimir Mikulik, et al. ∙

∙ 10/15/2020

Avoiding Side Effects By Considering Future Tasks

Designing reward functions is difficult: the designer has to specify wha...

22 Victoria Krakovna, et al. ∙

∙ 12/14/2018

Scaling shared model governance via model splitting

Currently the only techniques for sharing governance of a deep learning ...

6 Miljan Martic, et al. ∙

∙ 11/19/2018

Scalable agent alignment via reward modeling: a research direction

One obstacle to applying reinforcement learning algorithms to real-world...

20 Jan Leike, et al. ∙

∙ 06/04/2018

Measuring and avoiding side effects using relative reachability

How can we design reinforcement learning agents that avoid causing unnec...

2 Victoria Krakovna, et al. ∙

∙ 11/27/2017

AI Safety Gridworlds

We present a suite of reinforcement learning environments illustrating v...

0 Jan Leike, et al. ∙

∙ 06/12/2017

Deep reinforcement learning from human preferences

For sophisticated reinforcement learning (RL) systems to interact useful...

0 Paul Christiano, et al. ∙

Are you a researcher?
Expose your work
to one of the largest
A.I. communities in the world