Sam Devlin
Sam Devlin
Microsoft Research Cambridge
Geverifieerd e-mailadres voor microsoft.com - Homepage
Titel
Geciteerd door
Geciteerd door
Jaar
Dynamic potential-based reward shaping
SM Devlin, D Kudenko
Proceedings of the 11th International Conference on Autonomous Agents and …, 2012
1202012
Theoretical considerations of potential-based reward shaping for multi-agent systems
S Devlin, D Kudenko
The 10th International Conference on Autonomous Agents and Multiagent …, 2011
962011
Potential-based difference rewards for multiagent reinforcement learning
S Devlin, L Yliniemi, D Kudenko, K Tumer
Proceedings of the 2014 international conference on Autonomous agents and …, 2014
772014
An Empirical Study Of Potential-Based Reward Shaping And Advice In Complex, Multi-Agent Systems
S Devlin, D Kudenko, M Grześ
Advances in Complex Systems (ACS) 14 (02), 251-278, 2011
722011
From value chains to technological platforms: The effects of crowdfunding in the digital game industry
A Nucciarelli, F Li, KJ Fernandes, N Goumagias, I Cabras, S Devlin, ...
Journal of Business Research 78, 341-352, 2017
642017
Predicting player disengagement and first purchase with event-frequency based data representation
H Xie, S Devlin, D Kudenko, P Cowling
2015 IEEE Conference on Computational Intelligence and Games (CIG), 230-237, 2015
522015
Expressing arbitrary reward functions as potential-based advice
A Harutyunyan, S Devlin, P Vrancx, A Nowé
Proceedings of the AAAI Conference on Artificial Intelligence 29 (1), 2015
422015
Policy invariance under reward transformations for multi-objective reinforcement learning
P Mannion, S Devlin, K Mason, J Duggan, E Howley
Neurocomputing 263, 60-73, 2017
242017
Resource abstraction for reinforcement learning in multiagent congestion problems
K Malialis, S Devlin, D Kudenko
arXiv preprint arXiv:1903.05431, 2019
232019
Dynamic economic emissions dispatch optimisation using multi-agent reinforcement learning
P Mannion, K Mason, S Devlin, J Duggan, E Howley
Proceedings of the Adaptive and Learning Agents workshop (at AAMAS 2016), 2016
232016
Multi-objective dynamic dispatch optimisation using multi-agent reinforcement learning
P Mannion, K Mason, S Devlin, J Duggan, E Howley
Proceedings of the 2016 International Conference on Autonomous Agents …, 2016
222016
Potential-based reward shaping for finite horizon online pomdp planning
A Eck, LK Soh, S Devlin, D Kudenko
Autonomous Agents and Multi-Agent Systems 30 (3), 403-445, 2016
212016
Combining gameplay data with monte carlo tree search to emulate human play
S Devlin, A Anspoka, N Sephton, P Cowling, J Rollason
Proceedings of the AAAI Conference on Artificial Intelligence and …, 2016
192016
Game Intelligence
S Devlin, PI Cowling, D Kudenko, N Goumagias, A Nucciareli, I Cabras, ...
2014 IEEE Conference on Computational Intelligence and Games, 1-8, 2014
192014
Exploring survival rates of companies in the UK video-games industry: An empirical study
I Cabras, ND Goumagias, K Fernandes, P Cowling, F Li, D Kudenko, ...
Technological forecasting and social change 117, 305-314, 2017
172017
Generalization in reinforcement learning with selective noise injection and information bottleneck
M Igl, K Ciosek, Y Li, S Tschiatschek, C Zhang, S Devlin, K Hofmann
Advances in neural information processing systems, 13978-13990, 2019
162019
Narrative bytes: Data-driven content production in esports
F Block, V Hodge, S Hobson, N Sephton, S Devlin, MF Ursu, A Drachen, ...
Proceedings of the 2018 ACM International Conference on Interactive …, 2018
162018
Win prediction in esports: Mixed-rank match prediction in multi-player online battle arena games
V Hodge, S Devlin, N Sephton, F Block, A Drachen, P Cowling
arXiv preprint arXiv:1711.06498, 2017
162017
Knowledge revision for reinforcement learning with abstract MDPs
K Efthymiadis, S Devlin, D Kudenko
Proceedings of the 2014 international conference on Autonomous agents and …, 2014
162014
The text-based adventure AI competition
T Atkinson, H Baier, T Copplestone, S Devlin, J Swan
IEEE Transactions on Games 11 (3), 260-266, 2019
152019
Het systeem kan de bewerking nu niet uitvoeren. Probeer het later opnieuw.
Artikelen 1–20