Nicolas Heess

Publications by Year

Research Areas

Reinforcement Learning in Robotics, Robot Manipulation and Learning, Adversarial Robustness in Machine Learning, Human Pose and Action Recognition, Robotic Locomotion and Control

Most-Cited Works

• Continuous control with deep reinforcement learning(2016)
• Recurrent Models of Visual Attention(2014)
• Deterministic policy gradient algorithms(2014)
• → Emergence of Locomotion Behaviours in Rich Environments(2017)668 cited
• → Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards(2017)509 cited
• Learning continuous control policies by stochastic value gradients(2015)
• → Distributed Distributional Deterministic Policy Gradients(2018)283 cited
• → Graph networks as learnable physics engines for inference and control(2018)280 cited