![]() ![]() ![]() We conduct an extensive evaluation with human players, learning agents with various input types and architectures, and heuristic agents with different strategies. By having such a design, we evaluate two distinct levels of generalization, namely local generalization and broad generalization. We create a wide variety of distinct task templates, and we ensure that all the task templates within the same scenario can be solved by using one specific strategic physical rule. Inspired by the physical knowledge acquired in infancy and the capabilities required for robots to operate in real-world environments, we identify 15 essential physical scenarios. To facilitate research addressing this problem, we propose a new testbed that requires an agent to reason about physical scenarios and take an action appropriately. Humans are well versed in reasoning about the behaviours of physical objects and choosing actions accordingly to accomplish tasks, while this remains a major challenge for artificial intelligence.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |