Agents
Delay and Cooperation in Nonstochastic Linear Bandits
This paper offers a nearly optimal algorithm for online linear optimization with delayed bandit feedback.
Modelling the Dynamics of Multiagent Q-Learning in Repeated Symmetric Games: a Mean Field Theoretic Approach
Shuyue Hu, Chin-wing Leung, Ho-fung Leung
Neural Information Processing Systems http://nips.cc/
Response about the significance and originality
The theoretical contributions of our work and the works [Mguni et al., AAAI'18; Mguni et al., AAMAS'19] mentioned
A Structured Prediction Approach for Generalization in Cooperative Multi-Agent Reinforcement Learning
Nicolas Carion, Nicolas Usunier, Gabriel Synnaeve, Alessandro Lazaric
Neural Information Processing Systems http://nips.cc/
Regret-Based Pruning in Extensive-Form Games
Neural Information Processing Systems http://nips.cc/
Equipping Experts/Bandits with Long-term Memory
Kai Zheng, Haipeng Luo, Ilias Diakonikolas, Liwei Wang
For both problems, the classical performance measure is the learner's (static) regret, defined as the difference between the learner's total loss and the loss of the best fixed action.
Fast and Furious Learning in Zero-Sum Games: Vanishing Regret with Non-Vanishing Step Sizes
This phenomenon, that we coin "fast and furious" learning in games, sets a new benchmark about what is possible both in max-min optimization as well as in multi-agent systems.