301 citations · 439 across the 27 of their papers we have counts for
5 papers · 1 filter
Learning Curricula in Open-Ended Worlds
Minqi Jiang
Deep reinforcement learning (RL) provides powerful methods for training optimal sequential decision-making agents. As collecting real-world interactions can entail additional costs…
A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs
Mikael Henaff, Minqi Jiang, Roberta Raileanu
Exploration in environments which differ across episodes has received increasing attention in recent years. Current methods use some combination of global novelty bonuses, computed…
General Intelligence Requires Rethinking Exploration
Minqi Jiang, Tim Rocktäschel, Edward Grefenstette
We are at the cusp of a transition from "learning from data" to "learning what data to learn from" as a central focus of artificial intelligence (AI) research. While the first-orde…
GriddlyJS: A Web IDE for Reinforcement Learning
Christopher Bamford, Minqi Jiang, Mikayel Samvelyan +1
Progress in reinforcement learning (RL) research is often driven by the design of new, challenging environments -- a costly undertaking requiring skills orthogonal to that of a typ…
WordCraft: An Environment for Benchmarking Commonsense Agents
Minqi Jiang, Jelena Luketina, Nantas Nardelli +4
The ability to quickly solve a wide range of real-world tasks requires a commonsense understanding of the world. Yet, how to best extract such knowledge from natural language corpo…