23 citations · 101 across the 30 of their papers we have counts for
3 papers · 1 filter
Utilizing Prior Solutions for Reward Shaping and Composition in Entropy-Regularized Reinforcement Learning
Jacob Adamczyk, Argenis Arriojas, Stas Tiomkin +1
In reinforcement learning (RL), the ability to utilize prior knowledge from previously solved tasks can allow agents to quickly solve new problems. In some cases, these new problem…
Intrinsic Motivation in Dynamical Control Systems
Stas Tiomkin, Ilya Nemenman, Daniel Polani +1
Biological systems often choose actions without an explicit reward signal, a phenomenon known as intrinsic motivation. The computational principles underlying this behavior remain…
Multi-Objective Policy Gradients with Topological Constraints
Kyle Hollins Wray, Stas Tiomkin, Mykel J. Kochenderfer +1
Multi-objective optimization models that encode ordered sequential constraints provide a solution to model various challenging problems including encoding preferences, modeling a c…