Learning with opponent-learning awareness
Multi-agent settings are quickly gathering importance in machine learning. This includes a plethora of recent work on deep multi-agent reinforcement learning, but also can be extended to hierarchical reinforcement learning, generative adversarial networks and decentralised optimization. In all these...
Main Authors: | Foerster, J, Chen, R, Al-Shedivat, M, Whiteson, S, Abbeel, P, Mordatch, I |
---|---|
Format: | Conference item |
Udgivet: |
International Foundation for Autonomous
Agents and Multiagent Systems
2018
|
Lignende værker
-
Stable opponent shaping in differentiable games
af: Letcher, A, et al.
Udgivet: (2019) -
Evolutionary dynamics of networked multi-person games: mixing opponent-aware and opponent-independent strategy decisions
af: Feng Huang, et al.
Udgivet: (2019-01-01) -
Deep learning with intelligent opponent in fencing
af: Loh, Qiao Yan
Udgivet: (2022) -
Learning to play against any mixture of opponents
af: Max Olan Smith, et al.
Udgivet: (2023-07-01) -
A baseline for any order gradient estimation in stochastic computation graphs
af: Mao, J, et al.
Udgivet: (2019)