301 citations · 439 across the 27 of their papers we have counts for
Showing 2020Show all
2 papers · 1 filter
cs.LG2020★ 4 cited
Prioritized Level Replay
Minqi Jiang, Edward Grefenstette, Tim Rocktäschel
Environments with procedurally generated content serve as important benchmarks for testing systematic generalization in deep reinforcement learning. In this setting, each level is…
cs.AI2020★ 10 cited
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…