Deep reinforcement learning produces robust locomotion policies for legged robots over challenging terrains. To date, few studies have leveraged model-based methods to combine these locomotion skills ...

Nvidia used GPT-4 to improve reinforcement learning for robots by crafting better rewards than human programmers could.

NVIDIA’s new Eureka “AI agent” utilizes GPT-4 by asking the large language model (LLM) to write its own reward-based reinforcement learning software code.