Soft Actor-Critic Algorithms and Applications
- Tuomas Haarnoja, Aurick Zhou, S. Levine
- Computer ScienceArXiv
- 13 December 2018
Soft Actor-Critic (SAC), the recently introduced off-policy actor-critic algorithm based on the maximum entropy RL framework, achieves state-of-the-art performance, outperforming prior on-policy and off- policy methods in sample-efficiency and asymptotic performance.
Learning to Walk via Deep Reinforcement Learning
- Tuomas Haarnoja, Aurick Zhou, Sehoon Ha, Jie Tan, G. Tucker, S. Levine
- Computer ScienceRobotics: Science and Systems
- 1 December 2018
A sample-efficient deep RL algorithm based on maximum entropy RL that requires minimal per-task tuning and only a modest number of trials to learn neural network policies is proposed and achieves state-of-the-art performance on simulated benchmarks with a single set of hyperparameters.
DART: Dynamic Animation and Robotics Toolkit
- Jeongseok Lee, Michael X. Grey, C. K. Liu
- Computer ScienceJournal of Open Source Software
- 6 February 2018
DART (Dynamic Animation and Robotics Toolkit) is a collaborative, cross-platform, open source library that features a multibody dynamic simulator and various kinematic tools for control and motion planning.
Learning to Walk in the Real World with Minimal Human Effort
- Sehoon Ha, P. Xu, Zhenyu Tan, S. Levine, Jie Tan
- Computer ScienceConference on Robot Learning
- 20 February 2020
This paper develops a system for learning legged locomotion policies with deep RL in the real world with minimal human effort by developing a multi-task learning procedure, an automatic reset controller, and a safety-constrained RL framework.
Learning to be Safe: Deep RL with a Safety Critic
- K. Srinivasan, Benjamin Eysenbach, Sehoon Ha, Jie Tan, Chelsea Finn
- Computer ScienceArXiv
- 27 October 2020
This work proposes to learn how to be safe in one set of tasks and environments, and then use that learned intuition to constrain future behaviors when learning new, modified tasks, and empirically studies this form of safety-constrained transfer learning in three challenging domains.
PODS: Policy Optimization via Differentiable Simulation
- Miguel Zamora, Momchil Peychev, Sehoon Ha, Martin T. Vechev, Stelian Coros
- Computer ScienceInternational Conference on Machine Learning
- 2021
This paper explores a systematic way of leveraging the additional information provided by an emerging class of differentiable simulators to directly compute the analytic gradient of a policy’s value function with respect to the actions it outputs and shows that this approach consistently leads to better asymptotic behavior across a set of payload manipulation tasks that demand a high degree of accuracy and precision.
Falling and landing motion control for character animation
A general controller is developed that allows the character to fall from a wide range of heights and initial speeds, continuously roll on the ground, and get back on its feet, without inducing large stress on joints at any moment.
Computational Design of Robotic Devices From High-Level Motion Specifications
- Sehoon Ha, Stelian Coros, A. Alspach, James M. Bern, Joohyung Kim, K. Yamane
- Computer ScienceIEEE Transactions on robotics
- 25 June 2018
A novel heuristic function estimates how much an intermediate robot design needs to change before it becomes able to execute the target motion trajectories, and demonstrates the effectiveness of this computational design method by automatically creating a variety of robotic manipulators and legged robots.
Computational co-optimization of design parameters and motion trajectories for robotic systems
- Sehoon Ha, Stelian Coros, A. Alspach, Joohyung Kim, K. Yamane
- Computer Science, EngineeringInt. J. Robotics Res.
- 5 June 2018
A novel computational approach to optimizing the morphological design of robots by optimizing the design parameters including link lengths and actuator placements whereas concurrently adjusting motion parameters such as joint trajectories, actuator inputs, and contact forces.
Joint Optimization of Robot Design and Motion Parameters using the Implicit Function Theorem
- Sehoon Ha, Stelian Coros, A. Alspach, Joohyung Kim, K. Yamane
- Computer ScienceRobotics: Science and Systems
- 12 July 2017
A novel computational approach to optimizing the morphological design of robots, which finds that the complex relationship between design and motion parameters can be established via sensitivity analysis if the robot’s movements are modeled as spatio-temporal solutions to optimal control problems.
...
...