2 papers
cs.LG2025
Learning Without Time-Based Embodiment Resets in Soft-Actor Critic
Homayoon Farrahi, A. Rupam Mahmood
When creating new reinforcement learning tasks, practitioners often accelerate the learning process by incorporating into the task several accessory components, such as breaking th…
cs.LG2024
Revisiting Scalable Hessian Diagonal Approximations for Applications in Reinforcement Learning
Mohamed Elsayed, Homayoon Farrahi, Felix Dangel +1
Second-order information is valuable for many applications but challenging to compute. Several works focus on computing or approximating Hessian diagonals, but even this simplifica…