16 citations · 32 across the 16 of their papers we have counts for
7 papers · 1 filter
All by Myself: Learning Individualized Competitive Behaviour with a Contrastive Reinforcement Learning optimization
Pablo Barros, Alessandra Sciutti
In a competitive game scenario, a set of agents have to learn decisions that maximize their goals and minimize their adversaries' goals at the same time. Besides dealing with the i…
Incorporating Rivalry in Reinforcement Learning for a Competitive Game
Pablo Barros, Ana Tanevska, Ozge Yalcin +1
Recent advances in reinforcement learning with social agents have allowed us to achieve human-level performance on some interaction tasks. However, most interactive scenarios do no…
Analysis of Social Robotic Navigation approaches: CNN Encoder and Incremental Learning as an alternative to Deep Reinforcement Learning
Janderson Ferreira, Agostinho A. F. Júnior, Letícia Castro +3
Dealing with social tasks in robotic scenarios is difficult, as having humans in the learning loop is incompatible with most of the state-of-the-art machine learning algorithms. Th…
CNN Encoder to Reduce the Dimensionality of Data Image for Motion Planning
Janderson Ferreira, Agostinho A. F. Júnior, Yves M. Galvão +2
Many real-world applications need path planning algorithms to solve tasks in different areas, such as social applications, autonomous cars, and tracking activities. And most import…
Learning from Learners: Adapting Reinforcement Learning Agents to be Competitive in a Card Game
Pablo Barros, Ana Tanevska, Alessandra Sciutti
Learning how to adapt to complex and dynamic environments is one of the most important factors that contribute to our intelligence. Endowing artificial agents with this ability is…
The Chef's Hat Simulation Environment for Reinforcement-Learning-Based Agents
Pablo Barros, Anne C. Bloem, Inge M. Hootsmans +4
To achieve social interactions within Human-Robot Interaction (HRI) environments is a very challenging task. Most of the current research focuses on Wizard-of-Oz approaches, which…