489 citations · 1.7k across the 57 of their papers we have counts for
3 papers · 1 filter
Galactic: Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-Per-Second
Vincent-Pierre Berges, Andrew Szot, Devendra Singh Chaplot +4
We present Galactic, a large-scale simulation and reinforcement-learning (RL) framework for robotic mobile manipulation in indoor environments. Specifically, a Fetch robot (equippe…
Neural Priming for Sample-Efficient Adaptation
Matthew Wallingford, Vivek Ramanujan, Alex Fang +5
We propose Neural Priming, a technique for adapting large pretrained models to distribution shifts and downstream tasks given few or no labeled examples. Presented with class names…
CORA: Benchmarks, Baselines, and Metrics as a Platform for Continual Reinforcement Learning Agents
Sam Powers, Eliot Xing, Eric Kolve +2
Progress in continual reinforcement learning has been limited due to several barriers to entry: missing code, high compute requirements, and a lack of suitable benchmarks. In this…