BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems
We present a new algorithm that significantly improves the efficiency of exploration for deep Q-learning agents in dialogue systems. Our agents explore via Thompson sampling, drawing Monte Carlo samples from a Bayes-by-Backprop neural network. Our algorithm learns much faster than common exploration strategies such as $\epsilon$-greedy, Boltzmann, bootstrapping, and intrinsic-reward-based ones. Additionally, we show that spiking the replay buffer with experiences from just a few successful episodes can make Q-learning feasible when it might otherwise fail.
Code (0)
등록된 구현이 없습니다.
Tasks
Deep Reinforcement LearningEfficient ExplorationQ-Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Task-Oriented Dialogue SystemsThompson SamplingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
An Efficient Task-Oriented Dialogue Policy: Evolutionary Reinforcement Learning Injected by Elite Individuals
Deep Reinforcement Learning (DRL) is widely used in task-oriented dialogue systems to optimize dialogue policy, but it struggles to balance exploration and exploitation due to the high dimensionality of state and action …
Deep Reinforcement LearningEvolutionary AlgorithmsTask-Oriented Dialogue SystemsBBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems
We present a new algorithm that significantly improves the efficiency of exploration for deep Q-learning agents in dialogue systems. Our agents explore via Thompson sampling, drawing Monte Carlo samples from a Bayes-by-B…
Deep Reinforcement LearningEfficient ExplorationQ-Learningreinforcement-learning+4Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems
In this work, we present a hybrid learning method for training task-oriented dialogue systems through online user interactions. Popular methods for learning task-oriented dialogues include applying reinforcement learning…
Dialogue State TrackingImitation Learningreinforcement-learningReinforcement Learning+2Rethinking Supervised Learning and Reinforcement Learning in Task-Oriented Dialogue Systems
Dialogue policy learning for task-oriented dialogue systems has enjoyed great progress recently mostly through employing reinforcement learning methods. However, these approaches have become very sophisticated. It is tim…
DecoderMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATIONreinforcement-learning+3Post-processing Networks: Method for Optimizing Pipeline Task-oriented Dialogue Systems using Reinforcement Learning
Many studies have proposed methods for optimizing the dialogue performance of an entire pipeline task-oriented dialogue system by jointly training modules in the system using reinforcement learning. However, these method…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Task-Oriented Dialogue Systems