C4.5: programs for machine learning
C4.5: programs for machine learning
Purposive behavior acquisition for a real robot by vision-based reinforcement learning
Machine Learning - Special issue on robot learning
Towards collaborative and adversarial learning:: a case study in robotic soccer
International Journal of Human-Computer Studies - Evolution and learning in multiagent systems
The CMUnited-97 Small Robot Team
RoboCup-97: Robot Soccer World Cup I
Co-evolving Soccer Softbot Team Coordination with Genetic Programming
RoboCup-97: Robot Soccer World Cup I
PRICAI '96 Proceedings of the 4th Pacific Rim International Conference on Artificial Intelligence: Topics in Artificial Intelligence
Using Decision Tree Confidence Factors for Multiagent Control
RoboCup-97: Robot Soccer World Cup I
Reinforcement learning: a survey
Journal of Artificial Intelligence Research
Karlsruhe Brainstormers - A Reinforcement Learning Approach to Robotic Soccer
RoboCup 2000: Robot Soccer World Cup IV
VQQL. Applying Vector Quantization to Reinforcement Learning
RoboCup-99: Robot Soccer World Cup III
Karlsruhe Brainstormers - Design Principles
RoboCup-99: Robot Soccer World Cup III
Recognizing Formations in Opponent Teams
RoboCup 2000: Robot Soccer World Cup IV
Reinforcement Learning for 3 vs. 2 Keepaway
RoboCup 2000: Robot Soccer World Cup IV
Layered Learning in Genetic Programming for a Cooperative Robot Soccer Problem
EuroGP '01 Proceedings of the 4th European Conference on Genetic Programming
The Body, the Mind or the Eye, First?
RoboCup-99: Robot Soccer World Cup III
Reinforcement learning of competitive and cooperative skills in soccer agents
Applied Soft Computing
Reinforcement learning based resource allocation in business process management
Data & Knowledge Engineering
N-learning: a reinforcement learning paradigm for multiagent systems
AI'05 Proceedings of the 18th Australian Joint conference on Advances in Artificial Intelligence
Hi-index | 0.00 |
We present a novel multi-agent learning paradigm called team-partitioned, opaque-transition reinforcement learning (TPOT-RL). TPOT-RL introduces the use of action-dependent features to generalize the state space. In our work, we use a learned action-dependent feature space to aid higher-level reinforcement learning. TPOT-RL is an effective technique to allow a team of agents to learn to cooperate towards the achievement of a specific goal. It is an adaptation of traditional RL methods that is applicable in complex, non-Markovian, multi-agent domains with large state spaces and limited training opportunities. TPOT-RL is fully implemented and has been tested in the robotic soccer domain, a complex, multi-agent framework. This paper presents the algorithmic details of TPOT-RL as well as empirical results demonstrating the effectiveness of the developed multi-agent learning approach with learned features.