465 citations · 1.8k across the 19 of their papers we have counts for
3 papers · 2 filters
Adaptive Online Planning for Continual Lifelong Learning
Kevin Lu, Igor Mordatch, Pieter Abbeel
We study learning control in an online reset-free lifelong learning scenario, where mistakes can compound catastrophically into the future and the underlying dynamics of the enviro…
Emergent Tool Use From Multi-Agent Autocurricula
Bowen Baker, Ingmar Kanitscheider, Todor Markov +4
Through multi-agent competition, the simple objective of hide-and-seek, and standard reinforcement learning algorithms at scale, we find that agents create a self-supervised autocu…
Multi-Agent Reinforcement Learning with Multi-Step Generative Models
Orr Krupnik, Igor Mordatch, Aviv Tamar
We consider model-based reinforcement learning (MBRL) in 2-agent, high-fidelity continuous control problems -- an important domain for robots interacting with other agents in the s…