Improving Intrinsic Exploration by Creating Stationary Objectives

1 code implementation • 27 Oct 2023 • Roger Creus Castanyer, Joshua Romoff, Glen Berseth

Several exploration objectives like count-based bonuses, pseudo-counts, and state-entropy maximization are non-stationary and hence are difficult to optimize for the agent.

Centralized control for multi-agent RL in a complex Real-Time-Strategy game

1 code implementation • 25 Apr 2023 • Roger Creus Castanyer

Multi-agent Reinforcement learning (MARL) studies the behaviour of multiple learning agents that coexist in a shared environment.

Multi-agent Reinforcement Learning

Which Design Decisions in AI-enabled Mobile Applications Contribute to Greener AI?

no code implementations • 28 Sep 2021 • Roger Creus Castanyer, Silverio Martínez-Fernández, Xavier Franch

Overall, we plan to model the accuracy and complexity of AI-enabled applications in operation with respect to their design decisions and will provide tools for allowing practitioners to gain consciousness of the quantitative relationship between the design decisions and the green characteristics of study.

Image Classification text-classification +1

Integration of Convolutional Neural Networks in Mobile Applications

1 code implementation • 11 Mar 2021 • Roger Creus Castanyer, Silverio Martínez-Fernández, Xavier Franch

In this paper, we study the performance of a system that integrates a DL model as a trade-off between the accuracy and the complexity.