Predictable Reinforcement Learning Dynamics through Entropy Rate Minimization

1 code implementation • 30 Nov 2023 • Daniel Jarne Ornia, Giannis Delimpaltadakis, Jens Kober, Javier Alonso-Mora

In Reinforcement Learning (RL), agents have no incentive to exhibit predictable behaviors, and are often pushed (through e. g. policy entropy regularization) to randomize their actions in favor of exploration.

Policy Gradient Methods reinforcement-learning +1

Bounded Robustness in Reinforcement Learning via Lexicographic Objectives

no code implementations • 30 Sep 2022 • Daniel Jarne Ornia, Licio Romao, Lewis Hammond, Manuel Mazo Jr., Alessandro Abate

Policy robustness in Reinforcement Learning may not be desirable at any cost: the alterations caused by robustness requirements from otherwise optimal policies should be explainable, quantifiable and formally verifiable.

reinforcement-learning Reinforcement Learning (RL)

Robust Event-Driven Interactions in Cooperative Multi-Agent Learning

1 code implementation • 7 Apr 2022 • Daniel Jarne Ornia, Manuel Mazo Jr

We present an approach to reduce the communication required between agents in a Multi-Agent learning system by exploiting the inherent robustness of the underlying Markov Decision Process.

Event-Based Communication in Distributed Q-Learning

no code implementations • 3 Sep 2021 • Daniel Jarne Ornia, Manuel Mazo Jr

We present an approach to reduce the communication of information needed on a Distributed Q-Learning system inspired by Event Triggered Control (ETC) techniques.

Q-Learning