Markov Models
Non-asymptotic Analysis of Biased Adaptive Stochastic Approximation
While these algorithms have been extensively studied, both theoretically and practically, see, e.g., [
Measuring Goal-Directedness
In order to build more useful AI systems, a natural inclination is to try to make them more agentic . But while agents built from language models are touted as the next big advance [Wang et al., 2024],
On the Role of Information Structure in Reinforcement Learning for Partially-Observable Sequential Teams and Games
In this paper, we formalize a novel reinforcement learning model which explicitly represents the information structure.
Universally Expressive Communication in Multi-Agent Reinforcement Learning
By observing that many existing protocols can be viewed as instances of graph neural networks (GNNs), we demonstrate the equivalence of joint action selection to node labelling.
On the Stochastic Stability of Deep Markov Models
This section proposes additional regularization methods for learning stable deep Markov models. The most direct approach is to include the stability conditions as extra penalties in the DMM loss function.