arXiv (Cornell University) · 2017 · 27 citations · 0 references
ComputingComputer ScienceArtificial IntelligenceMachine LearningRobot LearningDeep LearningExploration-exploitation TradeoffNeural NetworksPolicy LearningReinforcement LearningReinforcement Learning FoundationsAction Schema LearningDeep Reinforcement LearningPolicy Representation
In this paper, we introduce the Action Schema Network (ASNet): a neural network architecture for learning generalised policies for probabilistic planning problems. By mimicking the relational structure of planning problems, ASNets are able to adopt a weight-sharing scheme which allows the network to be applied to any problem from a given planning domain. This allows the cost of training the network to be amortised over all problems in that domain. Further, we propose a training method which balances exploration and supervised training on small problems to produce a policy which remains robust when evaluated on larger problems. In experiments, we show that ASNet's learning capability allows it to significantly outperform traditional non-learning planners in several challenging domains.