ELEMENTAL: Interactive Learning from Demonstrations and Vision-Language Models for Reward Design in Robotics
L Chen, M Gombolay - arXiv preprint arXiv:2411.18825, 2024 - arxiv.org
Reinforcement learning (RL) has demonstrated compelling performance in robotic tasks, but
its success often hinges on the design of complex, ad hoc reward functions. Researchers …
its success often hinges on the design of complex, ad hoc reward functions. Researchers …