Abstract
The Belief-Desire-Intention (BDI) approach to agent development has formed the basis for much of the research on architectures for autonomous agents. A key advantage of the BDI approach is that agents may pursue multiple intentions in parallel. However, previous approaches to managing possible interactions between concurrently executing intentions are limited to interactions between simple achievement goals (and in some cases maintenance goals). In this paper, we present a new approach to intention progression for agents with temporally extended goals which allow mixing reachability and invariant properties, e.g., “travel to location A while not exceeding a gradient of 5%”. Temporally extended goals may be specified at run-time (top-level goals), and as subgoals in plans. In addition, our approach allows human-authored plans and plans implemented as reinforcement learning policies to be freely mixed in an agent program, allowing the development of agents with 'neuro-symbolic' architectures.
Original language | English |
---|---|
Title of host publication | Proceedings of the 33rd International Joint Conference on Artificial Intelligence |
Subtitle of host publication | Main Track |
Editors | Kate Larson |
Pages | 292-301 |
Number of pages | 10 |
ISBN (Electronic) | 9781956792041 |
DOIs | |
Publication status | Published - 9 Aug 2024 |
Event | 33rd International Joint Conference on Artificial Intelligence, IJCAI 2024 - Jeju, Korea, Republic of Duration: 3 Aug 2024 → 9 Aug 2024 https://ijcai24.org/ |
Conference
Conference | 33rd International Joint Conference on Artificial Intelligence, IJCAI 2024 |
---|---|
Abbreviated title | IJCAI 202 |
Country/Territory | Korea, Republic of |
City | Jeju |
Period | 3/08/24 → 9/08/24 |
Internet address |