Multiagent Reinforcement Learning: Theoretical Framework and an Algorithm

By Junling Hu, Michael P. Wellman. 1998

Subfields: Reinforcement Learning, Game & Decision Theory

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Reinforcement Learning

In Game & Decision Theory

Citations in the corpus

Learning World Graphs to Accelerate Hierarchical Reinforcement Learning (2019, neutral): “Finally, the learned world graphs can potentially be applied beyond HRL, e.g., multi-tasking RL [42], structured exploration by using pivotal state as checkouts [25] or in multiagent settings [15, 45].”
Multi-agent Reinforcement Learning in Sequential Social Dilemmas (2017, background): “The generalsum case is significantly more challenging [31], and algorithms either have strong assumptions or need to either track several different potential equilibria per agent [32, 33], model other players to simplify the problem [34], or must find a Figure 3: Left: Gathering.”
Episodic Exploration for Deep Deterministic Policies: An Application to StarCraft Micromanagement Tasks (2016, background): “Most of the focus has been on learning agents in competitive environments with adaptive adversaries (e.g., [15, 13, 40]).”
Empirically Evaluating Multiagent Learning Algorithms (2014, background): “…size; − More detailed investigation of algorithm behavior on instances from single generators; − Investigation of additional algorithms like Hyper-Q (Tesauro, 2004) and Nash-Q (Hu and Wellman, 1998); − Study of N -player repeated games and stochastic games (along the lines of Vu et al. (2005)).”
Action Semantics Network: Considering the Effects of Actions in Multiagent Systems (2019, background): “However, there also exist a lot of challenges in multiagent systems (MASs) since agents’ behaviors are influenced by each other and the environment exhibits more stochasticity and uncertainties (Claus & Boutilier, 1998; Hu & Wellman, 1998; Bu et al., 2008; Hauwere et al., 2016).”
AWESOME: A general multiagent learning algorithm that converges in self-play and learns a best response against stationary opponents (2003, background): “This is also an active area of research in multiagent systems in computer science (e.g., (Littman, 1994; Hu & Wellman, 1998; Claus & Boutilier, 1998; Wang & Sandholm, 2002)).”
A Unified Analysis of Value-Function-Based Reinforcement-Learning Algorithms (1999, background): “Hu and Wellman (1998) extended the results of this section to nonzero-sum games.”
A Survey of Collectives (2004, background): “In particular, game theory [11, 19, 30, 87], mechanism design [82, 87], and multiagent reinforcement learning [53, 56, 112, 192] are fields that grapple with some of the issues encountered in the field of collectives.”
Deep Mean Field Games for Learning Optimal Behavior Policy of Large Populations (2017, background): “Even though there are generalizations to multi-agent settings (Hu et al. , 1998; Littman, 2001; Lowe et al. , 2017), the MDP and Markov game frameworks do not easily suggest how to represent systems involving thousands of interacting agents whose actions induce an optimal trajectory through time.”
Optimal Payoff Functions for Members of Collectives (2001, background): “These results also illustrate the substantial superiority of these payoff functions to the perhaps the most natural version of the economics technique of “endogenizing externalities”.”
Multi-agent deep reinforcement learning: a survey (2021, background): “This can be very important to render the learning process robust against the decision-making of other agents in the environment (Hu and Wellman 1998).”
Convergence and No-Regret in Multiagent Learning (2004, methodology): “Equilibrium learners [2, 3, 4] are one method of handling the loss of stationarity.”
An Empirical Study of AI Population Dynamics with Million-agent Reinforcement Learning (2017, methodology): “Q-learning methods such as minimax Q-learning (Hu, Wellman, and others 1998) and Nash Q-learning (Hu and Wellman 2003) have been proposed.”
Multiagent Reinforcement Learning for Multi-Robot Systems: A Survey (2004, methodology): “Second, it needs to be assumed that the belief about opponent strategies also can be factored and represented in some convenient form [47], [49].”
Analyzing and visualizing multiagent rewards in dynamic and stochastic domains (2008, background): “Creating high-performance reward structures that promote coordination is a critical step in designing successful multiagent learning algorithms [8,15,18,21,22,26,31].”