FoMo Rewards: Can we cast foundation models as reward functions?
CoRR(2023)
摘要
We explore the viability of casting foundation models as generic reward
functions for reinforcement learning. To this end, we propose a simple pipeline
that interfaces an off-the-shelf vision model with a large language model.
Specifically, given a trajectory of observations, we infer the likelihood of an
instruction describing the task that the user wants an agent to perform. We
show that this generic likelihood function exhibits the characteristics ideally
expected from a reward function: it associates high values with the desired
behaviour and lower values for several similar, but incorrect policies.
Overall, our work opens the possibility of designing open-ended agents for
interactive tasks via foundation models.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要