Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Posts
publications
Go-explore: a new approach for hard-exploration problems
arXiv, 2019
Introduces Go-Explore, an exploration algorithm capable of solving the grand-challenge hard-exploration Atari games Montezuma′s Revenge and Pitfall.
Download here
Reinforcement Learning Under Moral Uncertainty
arXiv, 2020
An ambitious goal for artificial intelligence is to create agents that behave ethically. Unfortunately, there is widespread disagreement about which ethical theory an agent should follow. This paper translates philosophical work on moral uncertainty into an RL algorithm and investigates how moral uncertainty can avoid extreme behavior compared to single theories.
Download here
Open Questions in Creating Safe Open-ended AI: Tensions Between Control and Creativity
ALIFE, 2020
Open-ended search algorithms are relatively unstudied in the field of AI safety and yet are starting to show increasing promise as a path to producing advanced AI. This paper discusses the safety implications of open-ended search algorithms in AI.
Download here
Estimating Q(s,s’) with Deep Deterministic Dynamics Gradients
ICML, 2020
In this paper, we introduce a novel form of value function, Q(s, s′). We highlight the benefits of this approach in terms of value function transfer, learning within redundant action spaces, and learning off-policy from state observations generated by sub-optimal or completely random policies.
Download here
Exploration Based Language Learning for Text-Based Games
IJCAI, 2020
This work presents an exploration and imitation-learning-based agent capable of state-of-the-art performance in playing text-based computer games using the Go-Explore exploration algorithm.
Download here
First return, then explore
Nature, 2021
The definite version of the Go-Explore algorithm. On top of the results from the original pre-print, it introduces a dynamic representation that supports all Atari games, a variant in which the exploration phase can be performed in stochastic environments, and demonstrates Go-Explore working in a robotics environment.
Download here