The Packet-World: A testbed for investigating situated multiagent systems
By Danny Weyns, Alexander Helleboogh, Tom Holvoet. 2005
30 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Management Science and Operations Research, Mechanical Engineering
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Shimon Whiteson
- Jakob N. Foerster
- Gregory Farquhar
- Chongjie Zhang
- Wendelin Böhmer
- Christian Schröder de Witt
- Nantas Nardelli
- Tonghan Wang
In Management Science and Operations Research
- Shimon Whiteson
- Gregory Farquhar
- Jakob N. Foerster
- Nantas Nardelli
- Filippos Christianos
- Stefano V. Albrecht
- Christian Schröder de Witt
- Wendelin Böhmer
In Mechanical Engineering
Citations in the corpus
- Counterfactual Multi-Agent Policy Gradients (2017, background): “Many simpler multi-agent settings, such as Predator-Prey (Tan, 1993) or Packet World (Weyns et al., 2005), by contrast, have full simulators with controlled randomness that can be freely set to any state in order to perfectly replay experiences.”
- Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning (2017, neutral): “This differs from standard multi-agent settings such as Packet World (Weyns et al., 2005) and simulated RoboCup (Hausknecht et al., 2016), where often entire episodes can be fully replayed and analysed.”