no code implementations • 16 Aug 2023 • Ziteng Cheng, Anthony Coache, Sebastian Jaimungal
Specifically, we prove that the agent's risk aversion can be identified as the number of questions tends to infinity, and the questions are randomly designed.
no code implementations • 27 Feb 2023 • Ziteng Cheng, Sebastian Jaimungal, Nick Martin
We introduce a distributional method for learning the optimal policy in risk averse Markov decision process with finite state action spaces, latent costs, and stationary dynamics.