Erik Wijmans

Habitat 2.0: Training Home Assistants to Rearrange their Habitat

2021 · arXiv (Cornell University)

We introduce Habitat 2.0 (H2.0), a simulation platform for training virtual robots in interactive 3D environments and complex physics-enabled scenarios. We make comprehensive contributions to all levels of the embodied AI stack - data, simulation, …

VER: Scaling On-Policy RL Leads to the Emergence of Navigation in Embodied Rearrangement

2022 · arXiv (Cornell University)

We present Variable Experience Rollout (VER), a technique for efficiently scaling batched on-policy reinforcement learning in heterogenous environments (where different environments take vastly different times to generate rollouts) to many GPUs residing on, potentially, many …