D Ding, CY Wei, K Zhang… - … Conference on Machine …, 2022 - proceedings.mlr.press
We examine global non-asymptotic convergence properties of policy gradient methods for multi-agent reinforcement learning (RL) problems in Markov potential games (MPGs). To …
X Guo, A Hu, R Xu, J Zhang - Advances in neural …, 2019 - proceedings.neurips.cc
This paper presents a general mean-field game (GMFG) framework for simultaneous learning and decision-making in stochastic games with a large population. It first establishes …
S Perrin, J Pérolat, M Laurière… - Advances in neural …, 2020 - proceedings.neurips.cc
In this paper, we deepen the analysis of continuous time Fictitious Play learning algorithm to the consideration of various finite state Mean Field Game settings (finite horizon, $\gamma …
T Landgraf, GHW Gebhardt, D Bierbach… - Annual Review of …, 2021 - annualreviews.org
Biomimetic robots that replace living social interaction partners can help elucidate the underlying interaction rules in animal groups. Our review focuses on the use of interactive …
K Cui, H Koeppl - International Conference on Artificial …, 2021 - proceedings.mlr.press
The recent mean field game (MFG) formalism facilitates otherwise intractable computation of approximate Nash equilibria in many-agent settings. In this paper, we consider discrete-time …
Non-cooperative and cooperative games with a very large number of players have many applications but remain generally intractable when the number of players increases …
J Subramanian, A Mahajan - … of the 18th International Conference on …, 2019 - cim.mcgill.ca
Multi-agent reinforcement learning (MARL) refers to systems in which multiple agents are acting in a common and unknown environment. The presence of other agents makes MARL …
Concave Utility Reinforcement Learning (CURL) extends RL from linear to concave utilities in the occupancy measure induced by the agent's policy. This encompasses not only RL but …
We study infinite horizon discounted mean field control (MFC) problems with common noise through the lens of mean field Markov decision processes (MFMDP). We allow the agents to …