Learning and Reasoning for Robot Dialog and Navigation Tasks

no code implementations • SIGDIAL (ACL) 2020 • Keting Lu, Shiqi Zhang, Peter Stone, Xiaoping Chen

More interestingly, the robot was able to learn from navigation tasks to improve its dialog strategies.

reinforcement-learning Reinforcement Learning (RL)

Adaptive Dialog Policy Learning with Hindsight and User Modeling

no code implementations • SIGDIAL (ACL) 2020 • Yan Cao, Keting Lu, Xiaoping Chen, Shiqi Zhang

Reinforcement learning methods have been used to compute dialog policies from language-based interaction experiences.

Reinforcement Learning (RL)

AutoEG: Automated Experience Grafting for Off-Policy Deep Reinforcement Learning

no code implementations • 22 Apr 2020 • Keting Lu, Shiqi Zhang, Xiaoping Chen

First, we develop an algorithm, called Experience Grafting (EG), to enable RL agents to reorganize segments of the few high-quality trajectories from the experience pool to generate many synthetic trajectories while retaining the quality.

reinforcement-learning Reinforcement Learning (RL)

Robot Representation and Reasoning with Knowledge from Reinforcement Learning

no code implementations • 28 Sep 2018 • Keting Lu, Shiqi Zhang, Peter Stone, Xiaoping Chen

In this work, we integrate logical-probabilistic KRR with model-based RL, enabling agents to simultaneously reason with declarative knowledge and learn from interaction experiences.

reinforcement-learning Reinforcement Learning (RL)

Goal-oriented Dialogue Policy Learning from Failures

no code implementations • 20 Aug 2018 • Keting Lu, Shiqi Zhang, Xiaoping Chen

Reinforcement learning methods have been used for learning dialogue policies.

reinforcement-learning Reinforcement Learning (RL)