61 citations · 172 across the 10 of their papers we have counts for
11 papers
Computing the Newton-step faster than Hessian accumulation
Akshay Srinivasan, Emanuel Todorov
Computing the Newton-step of a generic function with decision variables takes flops. In this paper, we show that given the computational graph of the function, this bo…
Lyceum: An efficient and scalable ecosystem for robot learning
Colin Summers, Kendall Lowrey, Aravind Rajeswaran +2
We introduce Lyceum, a high-performance computational ecosystem for robot learning. Lyceum is built on top of the Julia programming language and the MuJoCo physics simulator, combi…
Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control
Kendall Lowrey, Aravind Rajeswaran, Sham Kakade +2
We propose a plan online and learn offline (POLO) framework for the setting where an agent, with an internal model, needs to continually act and learn in the world. Our work builds…
Reinforcement learning for non-prehensile manipulation: Transfer from simulation to physical system
Kendall Lowrey, Svetoslav Kolev, Jeremy Dao +2
Reinforcement learning has emerged as a promising methodology for training robot controllers. However, most results have been limited to simulation due to the need for a large numb…
Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations
Aravind Rajeswaran, Vikash Kumar, Abhishek Gupta +4
Dexterous multi-fingered hands are extremely versatile and provide a generic way to perform a multitude of tasks in human-centric environments. However, effectively controlling the…
Towards Generalization and Simplicity in Continuous Control
Aravind Rajeswaran, Kendall Lowrey, Emanuel Todorov +1
This work shows that policies with simple linear and RBF parameterizations can be trained to solve a variety of continuous control tasks, including the OpenAI gym benchmarks. The p…