Google
Google Scholar
Semantic Scholar
MS Academic
CiteSeerX
ORCIDKagan Tumer
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2020
[j42]Jen Jen Chung
, Damjan Miklic, Lorenzo Sabattini, Kagan Tumer, Roland Siegwart:
The impact of agent definitions and interactions on multiagent learning for coordination in traffic management domains. Auton. Agents Multi Agent Syst. 34(1): 21 (2020)- [c102]Gaurav Dixit, Stéphane Airiau, Kagan Tumer:
Gaussian Processes as Multiagent Reward Models. AAMAS 2020: 330-338 - [c101]Golden Rockefeller, Shauharda Khadka, Kagan Tumer:
Multi-level Fitness Critics for Cooperative Coevolution. AAMAS 2020: 1143-1151 - [c100]Nicholas Zerbel, Kagan Tumer:
The Power of Suggestion. AAMAS 2020: 1602-1610 - [c99]Connor Yates, Reid Christopher, Kagan Tumer:
Multi-fitness learning for behavior-driven cooperation. GECCO 2020: 453-461 - [c98]Somdeb Majumdar, Shauharda Khadka, Santiago Miret, Stephen McAleer, Kagan Tumer:
Evolutionary Reinforcement Learning for Sample-Efficient Multiagent Coordination. ICML 2020: 6651-6660
2010 – 2019
- 2019
- [j41]Daniel Hulse, Kagan Tumer, Christopher Hoyle, Irem Y. Tumer:
Modeling multidisciplinary design with multiagent learning. Artif. Intell. Eng. Des. Anal. Manuf. 33(1): 85-99 (2019) - [j40]Jen Jen Chung, Carrie Rebhuhn, Connor Yates, Geoffrey A. Hollinger, Kagan Tumer:
A multiagent framework for learning dynamic traffic management strategies. Auton. Robots 43(6): 1375-1391 (2019) - [j39]Shauharda Khadka, Jen Jen Chung, Kagan Tumer:
Neuroevolution of a Modular Memory-Augmented Neural Network for Deep Memory Problems. Evol. Comput. 27(4): 639-664 (2019) - [c97]Jen Jen Chung, Damjan Miklic, Lorenzo Sabattini, Kagan Tumer, Roland Siegwart:
The Impact of Agent Definitions and Interactions on Multiagent Learning for Coordination. AAMAS 2019: 1752-1760 - [c96]Shauharda Khadka, Connor Yates, Kagan Tumer:
Memory based Multiagent One Shot Learning. AAMAS 2019: 2054-2056 - [c95]Golden Rockefeller, Patrick Mannion, Kagan Tumer:
Curriculum Learning for Tightly Coupled Multiagent Systems. AAMAS 2019: 2174-2176 - [c94]Shauharda Khadka, Somdeb Majumdar, Tarek Nassar, Zach Dwiel, Evren Tumer, Santiago Miret, Yinyin Liu, Kagan Tumer:
Collaborative Evolutionary Reinforcement Learning. ICML 2019: 3341-3350 - [c93]Shauharda Khadka, Connor Yates, Kagan Tumer:
Memory-Based Multiagent One-Shot Learning: Extended Abstract. MRS 2019: 145-147 - [c92]Gaurav Dixit, Nicholas Zerbel, Kagan Tumer:
Dirichlet-Multinomial Counterfactual Rewards for Heterogeneous Multiagent Systems. MRS 2019: 209-215 - [c91]Golden Rockefeller, Patrick Mannion, Kagan Tumer:
Fitness Critics for Multiagent Learning: Extended Abstract. MRS 2019: 222-224 - [i15]Shauharda Khadka, Somdeb Majumdar, Tarek Nassar, Zach Dwiel, Evren Tumer, Santiago Miret, Yinyin Liu, Kagan Tumer:
Collaborative Evolutionary Reinforcement Learning. CoRR abs/1905.00976 (2019) - [i14]Shauharda Khadka, Somdeb Majumdar, Kagan Tumer:
Evolutionary Reinforcement Learning for Sample-Efficient Multiagent Coordination. CoRR abs/1906.07315 (2019) - 2018
- [j38]Nicolás F. Soria Zurita, Mitchell K. Colby, Irem Y. Tumer, Christopher Hoyle, Kagan Tumer:
Design of Complex Engineered Systems Using Multi-Agent Coordination. J. Comput. Inf. Sci. Eng. 18(1) (2018) - [c90]Jen Jen Chung, Scott Chow, Kagan Tumer:
When Less is More: Reducing Agent Noise with Probabilistically Learning Agents. AAMAS 2018: 1900-1902 - [c89]Shauharda Khadka, Connor Yates, Kagan Tumer:
A Memory-based Multiagent Framework for Adaptive Decision Making. AAMAS 2018: 1977-1979 - [c88]Shauharda Khadka, Kagan Tumer:
Evolution-Guided Policy Gradient in Reinforcement Learning. NeurIPS 2018: 1196-1208 - [i13]Shauharda Khadka, Kagan Tumer:
Evolutionary Reinforcement Learning. CoRR abs/1805.07917 (2018) - 2017
- [j37]Mitchell K. Colby, Kagan Tumer:
Fitness function shaping in multiagent cooperative coevolutionary algorithms. Auton. Agents Multi Agent Syst. 31(2): 179-206 (2017) - [c87]Shauharda Khadka, Jen Jen Chung, Kagan Tumer:
Evolving memory-augmented neural architecture for deep memory problems. GECCO 2017: 441-448 - [c86]Shauharda Khadka, Jen Jen Chung, Kagan Tumer:
Memory-augmented multi-robot teams that learn to adapt. MRS 2017: 128-134 - [c85]Callie Branyan, Chloe Fleming, Jacquelin Remaley, Ammar Kothari, Kagan Tumer, Ross L. Hatton, Yigit Mengüç:
Soft snake robots: Mechanical design and geometric gait implementation. ROBIO 2017: 282-289 - 2016
- [j36]Mitchell K. Colby, Logan Michael Yliniemi, Kagan Tumer:
Autonomous Multiagent Space Exploration with High-Level Human Feedback. J. Aerosp. Inf. Syst. 13(8): 301-315 (2016) - [j35]Chris HolmesParker, Adrian K. Agogino, Kagan Tumer:
Combining reward shaping and hierarchies for scaling to large multiagent systems. Knowl. Eng. Rev. 31(1): 3-18 (2016) - [j34]Logan Michael Yliniemi, Kagan Tumer:
Multi-objective multiagent credit assignment in reinforcement learning and NSGA-II. Soft Comput. 20(10): 3869-3887 (2016) - [c84]Logan Michael Yliniemi, Kagan Tumer:
Using Awareness to Promote Richer, More Human-Like Behaviors in Artificial Agents. AAMAS Workshops (Visionary Papers) 2016: 122-133 - [c83]Mitchell K. Colby, Theodore Duchow-Pressley, Jen Jen Chung, Kagan Tumer:
Local Approximation of Difference Evaluation Functions. AAMAS 2016: 521-529 - [c82]Mitchell K. Colby, Logan Michael Yliniemi, Paolo Pezzini, David Tucker, Kenneth Mark Bryden, Kagan Tumer:
Multiobjective Neuroevolutionary Control for a Fuel Cell Turbine Hybrid Energy System. GECCO 2016: 877-884 - [c81]Shauharda Khadka, Kagan Tumer, Mitchell K. Colby, Dave Tucker, Paolo Pezzini, Kenneth Mark Bryden:
Neuroevolution of a Hybrid Power Plant Simulator. GECCO 2016: 917-924 - [c80]Aida Rahmattalabi, Jen Jen Chung, Mitchell K. Colby, Kagan Tumer:
D++: Structural credit assignment in tightly coupled multiagent domains. IROS 2016: 4424-4429 - 2015
- [j33]Atil Iscen, Ken Caluwaerts, Jonathan Bruce, Adrian K. Agogino, Vytas SunSpiral, Kagan Tumer:
Learning Tensegrity Locomotion Using Open-Loop Control Signals and Coevolutionary Algorithms. Artif. Life 21(2): 119-140 (2015) - [j32]Logan Michael Yliniemi, Adrian K. Agogino, Kagan Tumer:
Simulation of the introduction of new technologies in air traffic management. Connect. Sci. 27(3): 269-287 (2015) - [c79]Mitchell K. Colby, Sepideh Kharaghani, Chris HolmesParker, Kagan Tumer:
Counterfactual Exploration for Improving Multiagent Learning. AAMAS 2015: 171-179 - [c78]Logan Michael Yliniemi, Drew Wilson, Kagan Tumer:
Multi-Objective Multiagent Credit Assignment in NSGA-II Using Difference Evaluations. AAMAS 2015: 1635-1636 - [c77]Mitchell K. Colby, William J. Curran, Kagan Tumer:
Approximating Difference Evaluations with Local Information. AAMAS 2015: 1659-1660 - [c76]Mitchell K. Colby, Kagan Tumer:
A Replicator Dynamics Analysis of Difference Evaluation Functions. AAMAS 2015: 1661-1662 - [c75]Mitchell K. Colby, Kagan Tumer:
An Evolutionary Game Theoretic Analysis of Difference Evaluation Functions. GECCO 2015: 1391-1398 - [c74]Andrew Gabler, Mitchell K. Colby, Kagan Tumer:
Learning Based Control of a Fuel Cell Turbine Hybrid Power System. GECCO (Companion) 2015: 1393-1394 - [c73]Logan Michael Yliniemi, Kagan Tumer:
Complete Multi-Objective Coverage with PaCcET. GECCO (Companion) 2015: 1525-1526 - [c72]Carrie Rebhuhn, Ryan Skeele, Jen Jen Chung, Geoffrey A. Hollinger, Kagan Tumer:
Learning to trick cost-based planners into cooperative behavior. IROS 2015: 4627-4633 - [c71]Mitchell K. Colby, Jen Jen Chung, Kagan Tumer:
Implicit adaptive multi-robot coordination in dynamic environments. IROS 2015: 5168-5173 - 2014
- [j31]Logan Michael Yliniemi, Adrian K. Agogino, Kagan Tumer:
Multirobot Coordination for Space Exploration. AI Mag. 35(4): 61-74 (2014) - [c70]Mitchell K. Colby, Matt Knudson, Kagan Tumer:
Multiagent Flight Control in Dynamic Environments with Cooperative Coevolutionary Algorithms. AAAI Spring Symposia 2014 - [c69]Carrie Rebhuhn, Matt Knudson, Kagan Tumer:
Announced Strategy Types in Multiagent RL for Conflict-Avoidance in the National Airspace. AAAI Spring Symposia 2014 - [c68]Sam Devlin, Logan Michael Yliniemi, Daniel Kudenko, Kagan Tumer:
Potential-based difference rewards for multiagent reinforcement learning. AAMAS 2014: 165-172 - [c67]Chris HolmesParker, Matthew E. Taylor, Adrian K. Agogino, Kagan Tumer:
CLEANing the reward: counterfactual actions to remove exploratory action noise in multiagent learning (extended abstract). AAMAS 2014: 1353-1354 - [c66]William J. Curran, Adrian K. Agogino, Kagan Tumer:
Using reward/utility based impact scores in partitioning. AAMAS 2014: 1563-1564 - [c65]Mitchell K. Colby, William J. Curran, Carrie Rebhuhn, Kagan Tumer:
Approximating difference evaluations with local knowledge. AAMAS 2014: 1577-1578 - [c64]William J. Curran, Adrian K. Agogino, Kagan Tumer:
Hierarchical simulation for complex domains: air traffic flow management. GECCO 2014: 1087-1094 - [c63]Logan Michael Yliniemi, Adrian K. Agogino, Kagan Tumer:
Evolutionary agent-based simulation of the introduction of new technologies in air traffic management. GECCO 2014: 1215-1222 - [c62]Atil Iscen, Adrian K. Agogino, Vytas SunSpiral, Kagan Tumer:
Flop and roll: Learning robust goal-directed locomotion for a Tensegrity Robot. IROS 2014: 2236-2243 - [c61]Logan Michael Yliniemi, Kagan Tumer:
PaCcET: An Objective Space Transformation to Iteratively Convexify the Pareto Front. SEAL 2014: 204-215 - [c60]Logan Michael Yliniemi, Kagan Tumer:
Multi-objective Multiagent Credit Assignment Through Difference Rewards in Reinforcement Learning. SEAL 2014: 407-418 - [c59]Chris HolmesParker, Matthew E. Taylor, Adrian K. Agogino, Kagan Tumer:
CLEAN Rewards to Improve Coordination by Removing Exploratory Action Noise. WI-IAT (3) 2014: 127-134 - 2013
- [j30]Kagan Tumer, Scott Proper:
Coordinating actions in congestion games: impact of top-down and bottom-up utilities. Auton. Agents Multi Agent Syst. 27(3): 419-443 (2013) - [j29]Matt Knudson, Kagan Tumer:
Dynamic Partnership Formation for Multi-Rover Coordination. Adv. Complex Syst. 16(1) (2013) - [j28]Jaime Junell, Kagan Tumer:
Robust predictive cruise control for commercial vehicles. Int. J. Gen. Syst. 42(7): 776-792 (2013) - [j27]Max Salichon, Kagan Tumer:
A neuro-evolutionary approach to control surface segmentation for micro aerial vehicles. Int. J. Gen. Syst. 42(7): 793-805 (2013) - [j26]MohammadJavad NoroozOliaee, Bechir Hamdaoui, Kagan Tumer:
Efficient Objective Functions for Coordinated Learning in Large-Scale Distributed OSA Systems. IEEE Trans. Mob. Comput. 12(5): 931-944 (2013) - [c58]Scott Proper, Kagan Tumer:
Multiagent Learning with a Noisy Global Reward Signal. AAAI 2013 - [c57]Logan Michael Yliniemi, Kagan Tumer:
Elo Ratings for Structural Credit Assignment in Multiagent Systems. AAAI (Late-Breaking Developments) 2013 - [c56]Mitchell K. Colby, Kagan Tumer:
Multiagent reinforcement learning in a distributed sensor network with indirect feedback. AAMAS 2013: 941-948 - [c55]Chris HolmesParker, Adrian K. Agogino, Kagan Tumer:
CLEAN rewards for improving multiagent coordination in the presence of exploration. AAMAS 2013: 1113-1114 - [c54]Chris HolmesParker, Adrian K. Agogino, Kagan Tumer:
Exploiting structure and utilizing agent-centric rewards to promote coordination in large multiagent systems. AAMAS 2013: 1181-1182 - [c53]Atil Iscen, Adrian K. Agogino, Vytas SunSpiral, Kagan Tumer:
Learning to control complex tensegrity robots. AAMAS 2013: 1193-1194 - [c52]Atil Iscen, Kagan Tumer:
Decentralized coordination via task decomposition and reward shaping. AAMAS 2013: 1269-1270 - [c51]Scott Proper, Kagan Tumer:
Graphical models in continuous domains for multiagent reinforcement learning. AAMAS 2013: 1277-1278 - [c50]William J. Curran, Adrian K. Agogino, Kagan Tumer:
Addressing hard constraints in the air traffic problem through partitioning and difference rewards. AAMAS 2013: 1281-1282 - [c49]William J. Curran, Adrian K. Agogino, Kagan Tumer:
Partitioning agents and shaping their evaluation functions in air traffic problems with hard constraints. GECCO (Companion) 2013: 183-184 - [c48]Atil Iscen, Adrian K. Agogino, Vytas SunSpiral, Kagan Tumer:
Controlling tensegrity robots through evolution. GECCO 2013: 1293-1300 - 2012
- [j25]Adrian K. Agogino, Kagan Tumer:
A multiagent approach to managing air traffic flow. Auton. Agents Multi Agent Syst. 24(1): 1-25 (2012) - [j24]Liz Sonenberg, Peter Stone, Kagan Tumer, Pinar Yolum:
Ten Years of AAMAS: Introduction to the Special Issue. AI Mag. 33(3): 11-13 (2012) - [j23]Ehsan M. Nasroullahi, Kagan Tumer:
Combining coordination mechanisms to improve performance in multi-robot teams. Artif. Intell. Res. 1(2): 1-10 (2012) - [j22]Bechir Hamdaoui, MohammadJavad NoroozOliaee, Kagan Tumer, Ammar Rayes:
Coordinating Secondary-User Behaviors for Inelastic Traffic Reward Maximization in Large-Scale \osa Networks. IEEE Trans. Netw. Serv. Manag. 9(4): 501-513 (2012) - [j21]Max Salichon, Kagan Tumer:
Evolving a Multiagent Controller for Micro Aerial Vehicles. IEEE Trans. Syst. Man Cybern. Part C 42(6): 1772-1783 (2012) - [c47]Mitchell K. Colby, Kagan Tumer:
Shaping fitness functions for coevolving cooperative multiagent systems. AAMAS 2012: 425-432 - [c46]Scott Proper, Kagan Tumer:
Modeling difference rewards for multiagent learning. AAMAS 2012: 1397-1398 - [c45]Adrian K. Agogino, Chris HolmesParker, Kagan Tumer:
Evolving distributed resource sharing for cubesat constellations. GECCO 2012: 1015-1022 - [c44]Adrian K. Agogino, Chris HolmesParker, Kagan Tumer:
Evolving large scale UAV communication system. GECCO 2012: 1023-1030 - [c43]Matt Knudson, Kagan Tumer:
Policy transfer in mobile robots using neuro-evolutionary navigation. GECCO (Companion) 2012: 1411-1412 - 2011
- [j20]Matt Knudson, Kagan Tumer:
Adaptive navigation for autonomous robots. Robotics Auton. Syst. 59(6): 410-420 (2011) - [c42]Christian Roth, Matt Knudson, Kagan Tumer:
Agent fitness functions for evolving coordinated sensor networks. GECCO 2011: 275-282 - [c41]Mitchell K. Colby, Ehsan M. Nasroullahi, Kagan Tumer:
Optimizing ballast design of wave energy converters using evolutionary algorithms. GECCO 2011: 1739-1746 - [c40]Bechir Hamdaoui, MohammadJavad NoroozOliaee, Kagan Tumer, Ammar Rayes:
Aligning Spectrum-User Objectives for Maximum Inelastic-Traffic Reward. ICCCN 2011: 1-6 - [c39]MohammadJavad NoroozOliaee, Bechir Hamdaoui, Kagan Tumer:
Achieving optimal elastic traffic rewards in dynamic multichannel access. HPCS 2011: 155-161 - [e1]Liz Sonenberg, Peter Stone, Kagan Tumer, Pinar Yolum:
10th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2011), Taipei, Taiwan, May 2-6, 2011, Volume 1-3. IFAAMAS 2011, ISBN 978-0-9826571-5-7 [contents] - [i12]Kagan Tumer, David H. Wolpert:
Collective Intelligence, Data Routing and Braess' Paradox. CoRR abs/1106.1821 (2011) - 2010
- [j19]Adrian K. Agogino, Kagan Tumer:
A Multiagent Coordination Approach to Robust Consensus Clustering. Adv. Complex Syst. 13(2): 165-197 (2010) - [c38]Matt Knudson, Kagan Tumer:
Robot coordination with ad-hoc team formation. AAMAS 2010: 1441-1442 - [c37]Matt Knudson, Kagan Tumer:
Coevolution of heterogeneous multi-robot teams. GECCO 2010: 127-134 - [c36]Max Salichon, Kagan Tumer:
A neuro-evolutionary approach to micro aerial vehicle control. GECCO 2010: 1123-1130 - [c35]Jack F. Shepherd III, Kagan Tumer:
Robust neuro-control for a micro quadrotor. GECCO 2010: 1131-1138
2000 – 2009
- 2009
- [j18]Kagan Tumer, Newsha Khani:
Learning from Actions not Taken in Multiagent Systems. Adv. Complex Syst. 12(4-5): 455-473 (2009) - [j17]Kagan Tumer, Adrian K. Agogino:
Multiagent Learning for Black Box System Reward Functions. Adv. Complex Syst. 12(4-5): 475-492 (2009) - [j16]Adrian K. Agogino, Kagan Tumer:
Learning Indirect Actions in Complex Domains: Action Suggestions for Air Traffic Control. Adv. Complex Syst. 12(4-5): 493-512 (2009) - [j15]Kagan Tumer, Adrian K. Agogino:
Improving Air Traffic Management with a Learning Multiagent System. IEEE Intell. Syst. 24(1): 18-21 (2009) - [c34]Kagan Tumer, John W. Lawson:
Coordinating Learning Agents for Multiple Resource Job Scheduling. ALA 2009: 123-140 - [c33]Adrian K. Agogino, Kagan Tumer:
Improving air traffic management through agent suggestions. AAMAS (2) 2009: 1271-1272 - [c32]Newsha Khani, Kagan Tumer:
Learning from actions not taken: a multiagent learning algorithm. AAMAS (2) 2009: 1277-1278 - [p2]Kagan Tumer, Zachary T. Welch, Adrian K. Agogino:
Traffic Congestion Management as a Learning Agent Coordination Problem. Multi-Agent Systems for Traffic and Transportation Engineering 2009: 261-279 - 2008
- [j14]Adrian K. Agogino, Kagan Tumer:
Analyzing and visualizing multiagent rewards in dynamic and stochastic domains. Auton. Agents Multi Agent Syst. 17(2): 320-338 (2008) - [j13]Adrian K. Agogino, Kagan Tumer:
Efficient Evaluation Functions for Evolving Coordination. Evol. Comput. 16(2): 257-288 (2008) - [j12]Nikunj C. Oza, Kagan Tumer:
Applications of ensemble methods. Inf. Fusion 9(1): 2-3 (2008) - [j11]Nikunj C. Oza, Kagan Tumer:
Classifier ensembles: Select real-world applications. Inf. Fusion 9(1): 4-20 (2008) - [j10]Kagan Tumer, Adrian K. Agogino:
Ensemble clustering with voting active clusters. Pattern Recognit. Lett. 29(14): 1947-1953 (2008) - [c31]Kagan Tumer, Adrian K. Agogino:
Adaptive Management of Air Traffic Flow: A Multiagent Coordination Approach. AAAI 2008: 1581-1584 - [c30]Adrian K. Agogino, Kagan Tumer:
Regulating air traffic flow with coupled agents. AAMAS (2) 2008: 535-542 - [c29]Kagan Tumer, Zachary T. Welch, Adrian K. Agogino:
Aligning social welfare and agent preferences to alleviate traffic congestion. AAMAS (2) 2008: 655-662 - 2007
- [c28]Kagan Tumer, Adrian K. Agogino:
Distributed agent-based air traffic flow management. AAMAS 2007: 255 - [c27]Adrian K. Agogino, Kagan Tumer:
Evolving distributed agents for managing air traffic. GECCO 2007: 1888-1895 - [p1]Kagan Tumer, Adrian K. Agogino:
Evolving Multi Rover Systems in Dynamic and Noisy Environments. Evolutionary Computation in Dynamic and Uncertain Environments 2007: 371-387 - 2006
- [j9]Adrian K. Agogino, Kagan Tumer:
Handling Communication Restrictions and Team Formation in Congestion Games. Auton. Agents Multi Agent Syst. 13(1): 97-115 (2006) - [c26]Adrian K. Agogino, Kagan Tumer:
QUICR-Learning for Multi-Agent Coordination. AAAI 2006: 1438-1443 - [c25]Nachi Gupta, Adrian K. Agogino, Kagan Tumer:
Efficient agent-based models for non-genomic evolution. AAMAS 2006: 58-64 - [c24]Adrian K. Agogino, Kagan Tumer:
Efficient agent-based cluster ensembles. AAMAS 2006: 1079-1086 - [c23]Kagan Tumer:
Coordinating simple and unreliable agents. AAMAS 2006: 1119-1121 - [c22]Adrian K. Agogino, Kagan Tumer:
Distributed evaluation functions for fault tolerant multi-rover systems. GECCO 2006: 1079-1086 - 2005
- [c21]Adrian K. Agogino, Kagan Tumer:
Multi-agent reward analysis for learning in noisy domains. AAMAS 2005: 81-88 - [c20]Kagan Tumer, Adrian K. Agogino:
Coordinating multi-rover systems: evaluation functions for dynamic and noisy environments. GECCO 2005: 591-598 - [c19]Adrian K. Agogino, Kagan Tumer, Risto Miikkulainen:
Efficient credit assignment through evaluation function decomposition. GECCO 2005: 1309-1316 - [c18]Kagan Tumer, Adrian K. Agogino:
Efficient Reward Functions for Adaptive Multi-rover Systems. LAMAS 2005: 177-191 - 2004
- [c17]Adrian K. Agogino, Kagan Tumer:
Unifying Temporal and Structural Credit Assignment Problems. AAMAS 2004: 980-987 - [c16]Kagan Tumer, Adrian K. Agogino:
Time-Extended Policies in Multi-Agent Reinforcement Learning. AAMAS 2004: 1338-1339 - [c15]Adrian K. Agogino, Kagan Tumer:
Efficient Evaluation Functions for Multi-rover Systems. GECCO (1) 2004: 1-11 - 2003
- [j8]