Kavosh Asadi

Latest

• Deep Radial-basis Value Functions for Continuous Control
• Lipschitz Lifelong Reinforcement Learning
• Smoothness in Reinforcement Learning with Large State and Action Space
• Research Statement
• Towards a Simple Approach to Multi-step Model-based Reinforcement Learning
• DeepMellow: Removing the Need for a Target Network in Deep Q-Learning
• State Abstraction as Compression in Apprenticeship Learning
• Equivalence between wasserstein and value-aware model-based reinforcement learning
• Lipschitz Continuity for Model-based Reinforcement Learning
• Mean Actor-Critic
• An Alternative Softmax Operator for Reinforcement Learning
• Hybrid Code Networks: Practical and Efficient End-to-end Dialog Control with Supervised and Reinforcement Learning
• Sample-efficient Deep Reinforcement Learning for Dialog Control