Programme
The workshop will take place on Tuesday, May 30 2023 in the afternoon session of the AAMAS conference, from 2pm to 6.30pm.
Tenative programme:
| Time | Talk |
|---|---|
| 14:00 - 14:40 | Invited talk: Alessandra Russo Symbolic Machine Learning and its role in Neuro-symbolic AI. Learning interpretable models from data is one of the main challenges of AI. Over the last two decades there has been a growing interest in Symbolic Machine Learning, a field of Machine Learning that aims to develop algorithms and systems for learning models that explain data in the context of some given background knowledge. In contrast to statistical learning, models learned by Symbolic Machine Learning are interpretable: they can be translated into natural language and understood by humans. In this talk, I will overview our state-ofthe- art symbolic machine learning system (ILASP) capable of learning different classes of models, (e.g., nonmonotonic, non-deterministic and preference-based) needed to solve a variety of real-world problems in a manner that is data efficient, scalable and robust to noise. The advanced features of this family of systems have made possible the development of innovative neuro-symbolic AI solutions that combine statistical learning for fast “low-level” perception from unstructured data, with “high-level” symbolic reasoning and learning of interpretable knowledge. I will then present our advances in neuro-symbolic AI and focus on two approaches that support respectively the learning of complex interpretable knowledge from unstructured data, and the discovery of subgoal structures for reinforcement learning agents. I will show that our neuro-symbolic solutions outperform purely differentiable baseline systems in accuracy and data efficiency. |
| 14:40 - 15:45 | Paper session: 10 min each + 2 min Q/A |
| Leo Ardon, Daniel Furelos Blanco and Alessandra Russo. Learning Reward Machines in Cooperative Multi-Agent Tasks | |
| Chentian Jiang, Nan Rosemary Ke and Hado van Hasselt. Learning How to Infer Partial MDPs for In-Context Adaptation and Exploration | |
| Vedran Galetic and Alistair Nottle. Flexible and Inherently Comprehensible Knowledge Representation for Data-Efficient Learning and Trustworthy Human-Machine Teaming in Manufacturing Environments | |
| Yexiang Xue, Maxwell Jacobson and Nan Jiang. “Embedding Constraint Reasoning in Structural Prediction, Content Generation and Imitation Learning” | |
| Louise Dennis, Marie Farrell and Michael Fisher. Developing Multi-Agent Systems with Degrees of Neuro-Symbolic Integration (position paper) | |
| 15:45 - 16:30 | Coffee break |
| 16:30 - 17:30 | NeSyMAS panel, chaired by Michael Fisher |