← Search

Homayoon Farrahi

2 accepted papers

2024

Revisiting Scalable Hessian Diagonal Approximations for Applications in Reinforcement Learning

ICML 2024poster

Second-order information is valuable for many applications but challenging to compute. Several works focus on computing or approximating Hessian diagonals, but even this simplification introduces significant additional costs compared to computing a gradient. In the absence of efficient exact computa…

2022

Model-free Policy Learning with Reward Gradients

AISTATS 2022poster

Despite the increasing popularity of policy gradient methods, they are yet to be widely utilized in sample-scarce applications, such as robotics. The sample efficiency could be improved by making best usage of available information. As a key component in reinforcement learning, the reward function i…