← Back to Benchmarks
simmediumsim-to-realmetric · varies

World-Gymnast: Training Robots with Reinforcement Learning in a World Model

Description

Robot learning from interacting with the physical world is fundamentally bottlenecked by the cost of physical interaction. The two alternatives, supervised finetuning (SFT) from expert demonstrations and reinforcement learning (RL) in a software-based simulator, are limited by the amount of expert data available and the sim-to-real gap for manipulation. With the recent emergence of world models learned from real-world video-action data, we ask the question of whether training a policy in a world

Source

http://arxiv.org/abs/2602.02454v1