Alert button
Picture for Karl Tuyls

Karl Tuyls

Alert button

SCC-rFMQ Learning in Cooperative Markov Games with Continuous Actions

Sep 18, 2018
Chengwei Zhang, Xiaohong Li, Jianye Hao, Siqi Chen, Karl Tuyls, Zhiyong Feng, Wanli Xue, Rong Chen

Figure 1 for SCC-rFMQ Learning in Cooperative Markov Games with Continuous Actions
Figure 2 for SCC-rFMQ Learning in Cooperative Markov Games with Continuous Actions
Figure 3 for SCC-rFMQ Learning in Cooperative Markov Games with Continuous Actions
Figure 4 for SCC-rFMQ Learning in Cooperative Markov Games with Continuous Actions
Viaarxiv icon

Negative Update Intervals in Deep Multi-Agent Reinforcement Learning

Sep 17, 2018
Gregory Palmer, Rahul Savani, Karl Tuyls

Figure 1 for Negative Update Intervals in Deep Multi-Agent Reinforcement Learning
Figure 2 for Negative Update Intervals in Deep Multi-Agent Reinforcement Learning
Figure 3 for Negative Update Intervals in Deep Multi-Agent Reinforcement Learning
Figure 4 for Negative Update Intervals in Deep Multi-Agent Reinforcement Learning
Viaarxiv icon

A Comparative Study of Bug Algorithms for Robot Navigation

Aug 17, 2018
Kimberly McGuire, Guido de Croon, Karl Tuyls

Figure 1 for A Comparative Study of Bug Algorithms for Robot Navigation
Figure 2 for A Comparative Study of Bug Algorithms for Robot Navigation
Figure 3 for A Comparative Study of Bug Algorithms for Robot Navigation
Figure 4 for A Comparative Study of Bug Algorithms for Robot Navigation
Viaarxiv icon

Fast Convergence for Object Detection by Learning how to Combine Error Functions

Aug 13, 2018
Benjamin Schnieders, Karl Tuyls

Figure 1 for Fast Convergence for Object Detection by Learning how to Combine Error Functions
Figure 2 for Fast Convergence for Object Detection by Learning how to Combine Error Functions
Figure 3 for Fast Convergence for Object Detection by Learning how to Combine Error Functions
Figure 4 for Fast Convergence for Object Detection by Learning how to Combine Error Functions
Viaarxiv icon

Relational Deep Reinforcement Learning

Jun 28, 2018
Vinicius Zambaldi, David Raposo, Adam Santoro, Victor Bapst, Yujia Li, Igor Babuschkin, Karl Tuyls, David Reichert, Timothy Lillicrap, Edward Lockhart, Murray Shanahan, Victoria Langston, Razvan Pascanu, Matthew Botvinick, Oriol Vinyals, Peter Battaglia

Figure 1 for Relational Deep Reinforcement Learning
Figure 2 for Relational Deep Reinforcement Learning
Figure 3 for Relational Deep Reinforcement Learning
Figure 4 for Relational Deep Reinforcement Learning
Viaarxiv icon

The Mechanics of n-Player Differentiable Games

Jun 06, 2018
David Balduzzi, Sebastien Racaniere, James Martens, Jakob Foerster, Karl Tuyls, Thore Graepel

Figure 1 for The Mechanics of n-Player Differentiable Games
Figure 2 for The Mechanics of n-Player Differentiable Games
Figure 3 for The Mechanics of n-Player Differentiable Games
Figure 4 for The Mechanics of n-Player Differentiable Games
Viaarxiv icon

Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input

Apr 11, 2018
Angeliki Lazaridou, Karl Moritz Hermann, Karl Tuyls, Stephen Clark

Figure 1 for Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input
Figure 2 for Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input
Figure 3 for Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input
Figure 4 for Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input
Viaarxiv icon

Emergent Communication through Negotiation

Apr 11, 2018
Kris Cao, Angeliki Lazaridou, Marc Lanctot, Joel Z Leibo, Karl Tuyls, Stephen Clark

Figure 1 for Emergent Communication through Negotiation
Figure 2 for Emergent Communication through Negotiation
Figure 3 for Emergent Communication through Negotiation
Figure 4 for Emergent Communication through Negotiation
Viaarxiv icon

SA-IGA: A Multiagent Reinforcement Learning Method Towards Socially Optimal Outcomes

Mar 08, 2018
Chengwei Zhang, Xiaohong Li, Jianye Hao, Siqi Chen, Karl Tuyls, Wanli Xue

Figure 1 for SA-IGA: A Multiagent Reinforcement Learning Method Towards Socially Optimal Outcomes
Figure 2 for SA-IGA: A Multiagent Reinforcement Learning Method Towards Socially Optimal Outcomes
Figure 3 for SA-IGA: A Multiagent Reinforcement Learning Method Towards Socially Optimal Outcomes
Figure 4 for SA-IGA: A Multiagent Reinforcement Learning Method Towards Socially Optimal Outcomes
Viaarxiv icon

Lenient Multi-Agent Deep Reinforcement Learning

Feb 27, 2018
Gregory Palmer, Karl Tuyls, Daan Bloembergen, Rahul Savani

Figure 1 for Lenient Multi-Agent Deep Reinforcement Learning
Figure 2 for Lenient Multi-Agent Deep Reinforcement Learning
Figure 3 for Lenient Multi-Agent Deep Reinforcement Learning
Figure 4 for Lenient Multi-Agent Deep Reinforcement Learning
Viaarxiv icon