A collection of peer-reviewed research articles and conference proceedings from PEER project.
Enabling MCTS Explainability for Sequential Planning Through Computation Tree LogicZiyan An, Hendrik Baier, Abhishek Dubey, Ayan Mukhopadhyay, Meiyi Ma. 27th European Conference on Artificial Intelligence (ECAI 2024). MOMAland: Benchmarking Multi-Objective Multi-Agent Reinforcement LearningFlorian Felten, Umut Ucak, Hicham Azmani, Gao Peng, Willem Röpke, Hendrik Baier, Patrick Mannion, Diederik M. Roijers, Jordan K. Terry, El-Ghazali Talbi, Gregoire Danoy, Ann Nowé, Roxana Radulescu. Multi-Objective Decision Making Workshop at ECAI 2024. Model-Based Reinforcement Learning in Multi-Objective Environments with a Distributional CriticWillem Röpke, Diederik M Roijers, Ann Nowé, Roxana Radulescu, Hendrik Baier. Multi-Objective Decision Making Workshop at ECAI 2024 Decision Making in Non-Stationary Environments with Policy-Augmented Search(extended abstract), Ava Pettet, Yunuo Zhang, Baiting Luo, Kyle Wray, Hendrik Baier, Aron Laszka, Abhishek Dubey, Ayan Mukhopadhyay. International Conference on Autonomous Agents and Multiagent Systems (AAMAS) 2024In this section you will find our liaisons and partners.
Coming soonDeliverables of the PEER project, public deliverables can be downloaded.
Coming soon
TANGO
TANGO is a €7M EU-funded Horizon Europe project that aims to develop the theoretical foundations and the computational framework for synergistic human-machine decision making. The 4-year project will pave the way for the next generation of human-centric AI systems. The goal is to fully develop the enormous potential that AI holds in terms of positive impact on individuals, society and economy by establishing a symbiosis between humans and machines: people should feel they can trust the systems they interact with, in terms of reliability of their predictions and decisions, capacity of the systems to understand their needs, and guarantees that they are genuinely aiming at supporting them rather than some undisclosed third party. TANGO focuses on developing the theoretical foundations and the computational framework for synergistic human-machine decision making, framework that will be tested on four real-life case studies.
HumAIne
HumAIne researches, develops, validates, and promotes a novel Operating System for Human-AI collaboration. This system facilitates advanced decision-making applications in dynamic, unstructured environments across various industrial sectors. By leveraging cutting-edge technologies such as Active Learning (AL), Neuro-Symbolic Learning (NL), Swarm Learning (SL), and eXplainable AI (XAI), all integrated into the HumAIne OS platform, HumAIne empowers AI solution integrators to create collaboration systems that surpass the capabilities of AI and humans working independently.
AI4REALNET
HumAIne researches, develops, validates, and promotes a novel Operating System for Human-AI collaboration. This system facilitates advanced decision-making applications in dynamic, unstructured environments across various industrial sectors. By leveraging cutting-edge technologies such as Active Learning (AL), Neuro-Symbolic Learning (NL), Swarm Learning (SL), and eXplainable AI (XAI), all integrated into the HumAIne OS platform, HumAIne empowers AI solution integrators to create collaboration systems that surpass the capabilities of AI and humans working independently.
THEMIS 5.0
THEMIS 5.0 is making AI decisions easier to understand. We are accelerating the shift towards more trusted AI-enabled services by helping people unpack the 'black box' that are AI algorithms to better understand what data is used, and how decisions are reached, so they can influence improvements. Using a risk-based approach, our AI trustworthiness framework and intelligent coach will create an ecosystem through which AI-driven hybrid decision making occurs in accordance with the needs and moral values of specific users. Our co-creation, development and testing processes are taking place across three use case domains - healthcare, port logistics and journalism.
Subscribe to our newsletter to get the latest news and updates.
