Proceedings of the AAAI Conference on Artificial Intelligence · 2017 · 18 citations · 14 references
ComputingAutonomous SystemsComputer ScienceArtificial IntelligenceDistributed SystemsMachine LearningConsensus AlgorithmsDistributed AlgorithmsDistributed ComputingMulti-agent SystemsMulti-task LearningReinforcement LearningConsensusConvergenceDecentralized LearningMulti-agent Policy LearningMulti-task Reinforcement LearningMultitask LearningScalabilityScalable Multi-agent Learning
Policy search reinforcement learning (RL) allows agents to learn autonomously with limited feedback. However, such methods typically require extensive experience for successful behavior due to their tabula rasa nature. Multitask RL is an approach, which aims to reduce data requirements by allowing knowledge transfer between tasks. Although successful, current multitask learning methods suffer from scalability issues when considering large number of tasks. The main reasons behind this limitation is the reliance on centralized solutions. This paper proposes to a novel distributed multitask RL framework, improving the scalability across many different types of tasks. Our framework maps multitask RL to an instance of general consensus and develops an efficient decentralized solver. We justify the correctness of the algorithm both theoretically and empirically: we first proof an improvement of convergence speed to an order of O(1/k) with k being the number of iterations, and then show our algorithm surpassing others on multiple dynamical system benchmarks.
14
Jan Peters, Stefan Schaal · Neurocomputing · 2008 · 751 citations
Policy search for motor primitives in robotics
Jens Kober, Jan Peters · Machine Learning · 2010 · 438 citations · Full text
Distributed Alternating Direction Method of Multipliers
Ermin Wei, Asuman Ozdaglar · 2012 · 407 citations · Full text
Consensus-based distributed support vector machines
2010 · 367 citations