Search Results for author:
Found 2 papers, 1 papers with code
Defining and Characterizing Reward Hacking
We provide the first formal definition of reward hacking, a phenomenon where optimizing an imperfect proxy reward function, $\mathcal{\tilde{R}}$, leads to poor performance according to the true reward function, $\mathcal{R}$.
Myriad: a real-world testbed to bridge trajectory optimization and deep learning
We present Myriad, a testbed written in JAX for learning and planning in real-world continuous environments.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
