Learning Density-Based Correlated Equilibria for Markov Games

no code implementations • 16 Feb 2023 • Libo Zhang, Yang Chen, Toru Takisaka, Bakh Khoussainov, Michael Witbrock, Jiamou Liu

In real-world multi-agent systems, in addition to being in an equilibrium, agents' policies are often expected to meet requirements with respect to safety, and fairness.

Fairness

Dynamic Shielding for Reinforcement Learning in Black-Box Environments

no code implementations • 27 Jul 2022 • Masaki Waga, Ezequiel Castellano, Sasinee Pruekprasert, Stefan Klikovits, Toru Takisaka, Ichiro Hasuo

The dynamic shielding technique constructs an approximate system model in parallel with RL using a variant of the RPNI algorithm and suppresses undesired explorations due to the shield constructed from the learned model.

reinforcement-learning Reinforcement Learning (RL)

Moment Propagation of Polynomial Systems Through Carleman Linearization for Probabilistic Safety Analysis

no code implementations • 21 Jan 2022 • Sasinee Pruekprasert, Jérémy Dubut, Toru Takisaka, Clovis Eberhart, Ahmet Cetinkaya

We develop a method to approximate the moments of a discrete-time stochastic polynomial system.