Stas Tiomkin

Control Capacity of Partially Observable Dynamic Systems in Continuous Time

2017 · arXiv (Cornell University)

Stochastic dynamic control systems relate in a prob- abilistic fashion the space of control signals to the space of corresponding future states. Consequently, stochastic dynamic systems can be interpreted as an information channel between the …

Leveraging Prior Knowledge in Reinforcement Learning via Double-Sided Bounds on the Value Function

2023 · arXiv (Cornell University)

An agent's ability to leverage past experience is critical for efficiently solving new tasks. Approximate solutions for new tasks can be obtained from previously derived value functions, as demonstrated by research on transfer learning, curriculum …