Kavosh Asadi

Sample-efficient Deep Reinforcement Learning for Dialog Control

2016 · arXiv (Cornell University)

Representing a dialog policy as a recurrent neural network (RNN) is attractive because it handles partial observability, infers a latent representation of state, and can be optimized with supervised learning (SL) or reinforcement learning (RL). …

Lipschitz Lifelong Reinforcement Learning

2021 · Proceedings of the AAAI Conference on Artificial Intelligence

We consider the problem of knowledge transfer when an agent is facing a series of Reinforcement Learning (RL) tasks. We introduce a novel metric between Markov Decision Processes and establish that close MDPs have close …

Learning the Target Network in Function Space

2024 · arXiv (Cornell University)

We focus on the task of learning the value function in the reinforcement learning (RL) setting. This task is often solved by updating a pair of online and target networks while ensuring that the parameters …

Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning

2017

End-to-end learning of recurrent neural networks (RNNs) is an attractive solution for dialog systems; however, current techniques are data-intensive and require thousands of dialogs to learn simple behaviors.