Value-function reinforcement learning in Markov games

By Michael L. Littman. 2001

442 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics

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

In Computational Theory and Mathematics

Citations in the corpus

Learning Multiagent Communication with Backpropagation (2016, methodology): “A ongst fully cooperative algorithm , many approaches [12, 15, 33] av id the need for communicat on by m king tr ng assumptions bout v sibility f oth r agents and the vironment.”
Factorized Q-learning for large-scale multi-agent systems (2018, background): “In the equilibrium learning paradigm, the agents try to learn policies which form aNash equilibrium [10].”
Independent reinforcement learners in cooperative Markov games: a survey regarding coordination problems (2012, background): “Joint action learners, on the contrary, are capable of perceiving (a posteriori) their actions and/or their rewards, for instance in (Littman, 2001; Hu & Wellman, 2003; Banerjee et al., 2004) to name a few.”
Application of reinforcement learning to the game of Othello (2008, methodology): “The minimax Q-learning algorithm described by Littman in [25,26] finds optimal policies in two-player zero-sum games using the minimax criterion.”
Crop Yield Prediction Using Deep Reinforcement Learning Model for Sustainable Agrarian Applications (2020, background): “A value function V (s,a) [56] is defined for each state-action pair is an estimate of the expected reward following a policy π .”
Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents (2018, methodology): “It is also worth noting that our model generalizes the team Markov game model for collaborative MARL, see Littman (2001); Wang and Sandholm (2003); Arslan and Y¨uksel (2017), where all agents have individual action sets but share a common payo ﬀ function as in the canonical MMDP.”
A Comprehensive Survey of Multiagent Reinforcement Learning (2008, unknown): “related to stability, whereas opponent-aware learning is related to adaptation [38], [59].”
Deep learning in medical image registration: a survey (2019, background): “Problems that use reinforcement learning can essentially be cast as Markov decision processes [75, 81, 98] associated with a tuple of a state, action, transition probability, reward, and discount factor.”
Large-Scale Order Dispatch in On-Demand Ride-Hailing Platforms: A Learning and Planning Approach (2018, background): “Multi-agent systems have been extensively studied in a variety of domains including robotic teams, resource management, distributed control, etc [1, 3, 9, 21].”
A Multiagent Reinforcement Learning Algorithm with Non-linear Dynamics (2008, unknown): “…learning (MARL) algorithms have been proposed and studied (Claus & Boutilier, 1998; Singh et al., 2000; Peshkin, Kim, Meuleau, & Kaelbling, 2000; Littman, 2001; Bowling & Veloso, 2002; Hu & Wellman, 2003; Bowling, 2005; Abdallah & Lesser, 2006; Conitzer & Sandholm, 2007; Banerjee & Peng, 2007).”
Algorithms for computing strategies in two-player simultaneous move games (2016, unknown): “Littman introduced Markov games to model these interactions as well as a variant of Q-learning called Minimax-Q to compute strategies [17, 18].”
Dynamic Safe Interruptibility for Decentralized Multi-Agent Reinforcement Learning (2017, methodology): “In non-cooperative games, neutral rules such as Nash-Q or minimax Q-learning [13] can be used, but they require each agent to know the Q-maps of the others.”
Game Theory and Multi-agent Reinforcement Learning (2012, background): “While the intensive research into value iteration based multi-agent RL has yielded some theoretical guarantees (Littman, 2001b), convergence results in the general Markov game case remain elusive.”
Parallel Reinforcement Learning (2002, unknown): “Keywords: Reinforcement Learning, Parallel Agents,Multi-AgentLearning”
Playing SNES in the Retro Learning Environment (2016, methodology): “More elaborate schemes are possible such as the minimax-Q algorithm (Littman, 1994), (Littman, 2001).”
QD-Learning: A Collaborative Distributed Strategy for Multi-Agent Reinforcement Learning Through Consensus + Innovations (2012, background): “Various formulations, ranging from general competitive dynamic stochastic games [11], [12], [13], [14] to so called fully cooperative [15], [16], [17], [18], [19], [20], [21], [22], have been investigated (see [10] for a more complete taxonomy).”
Multi-agent differential graphical games (2011, methodology): “RL methods have been used to solve multi-player games for finite-state systems in Busoniu, Babuska, and De Schutter (2008) and Littman (2001).”