Software


rllab

Software and Docs

rllab is a framework for developing and evaluating reinforcement learning algorithms. rllab provides a wrapper to run algorithms in rllab on environments from OpenAI Gym, as well as submitting the results to the OpenAI Gym scoreboard.

[121] Benchmarking Deep Reinforcement Learning for Continuous Control,
Yan Duan, Xi Chen, Rein Houthooft, John Schulman, Pieter Abbeel.
In the proceedings of the International Conference on Machine Learning (ICML), 2016. (arXiv 1604.06778, rllab:code, rllab:docs)


GPS: Guided Policy Search

Software and tutorial

End-to-End Training of Deep Visuomotor Policies,
Sergey Levine*, Chelsea Finn*, Trevor Darrell, Pieter Abbeel.
arXiv 1504.00702 (video)

[114] Deep Spatial Autoencoders for Visuomotor Learning
Chelsea Finn, Xin Yu Tan, Yan Duan, Trevor Darrell, Sergey Levine, Pieter Abbeel.
In the proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2016. (arXiv 1509.06113)

[113] Learning Deep Neural Network Policies with Continuous Memory States
Marvin Zhang, Zoe McCarthy, Chelsea Finn, Sergey Levine, Pieter Abbeel.
In the proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2016. (arXiv 1507.01273)

[94] Learning Contact-Rich Manipulation Skills with Guided Policy Search, Best Robotic Manipulation Paper Award,
Sergey Levine, Nolan Wagener, Pieter Abbeel.
In the proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2015. (pdf)

[80] Learning Neural Network Policies with Guided Policy Search under Unknown Dynamics,
Sergey Levine, Pieter Abbeel.
In Neural Information Processing Systems (NIPS) 27, 2015. (pdf)


trajopt: Trajectory Optimization for Motion Planning

trajopt is a software framework for generating robot trajectories by local optimization.

Software and tutorial

Papers

[57] Finding Locally Optimal, Collision-Free Trajectories with Sequential Convex Optimization,
John D. Schulman, Jonathan Ho, Alex Lee, Ibrahim Awwal, Henry Bradlow and Pieter Abbeel.
In the proceedings of Robotics: Science and Systems (RSS), 2013. (pdf, videos, code)

[66] Planning Locally Optimal, Curvature-Constrained Trajectories in 3D using Sequential Convex Optimization,
Yan Duan, Sachin Patil, John Schulman, Ken Goldberg, Pieter Abbeel.
In the proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2014. (pdf)

[70] Motion Planning with Sequential Convex Optimization and Convex Collision Checking,
John Schulman, Yan Duan, Jonathan Ho, Alex Lee, Ibrahim Awwal, Henry Bradlow, Jia Pan, Sachin Patil, Ken Goldberg, Pieter Abbeel.
In the International Journal of Robotics Research (IJRR), 2014. (pdf)