8 citations · 12 across the 6 of their papers we have counts for
6 papers
MA-Dreamer: Coordination and communication through shared imagination
Kenzo Lobos-Tsunekawa, Akshay Srinivasan, Michael Spranger
Multi-agent RL is rendered difficult due to the non-stationary nature of environment perceived by individual agents. Theoretically sound methods using the REINFORCE estimator are i…
How to Learn and Represent Abstractions: An Investigation using Symbolic Alchemy
Badr AlKhamissi, Akshay Srinivasan, Zeb-Kurth Nelson +1
Alchemy is a new meta-learning environment rich enough to contain interesting abstractions, yet simple enough to make fine-grained analysis tractable. Further, Alchemy provides an…
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…
Lower Bounds for Shoreline Searching with 2 or More Robots
Sumi Acharjee, Konstantinos Georgiou, Somnath Kundu +1
Searching for a line on the plane with unit speed robots is a classic online problem that dates back to the 50's, and for which competitive ratio upper bounds are known for eve…
Graphical Newton
Akshay Srinivasan, Emanuel Todorov
Computing the Newton step for a generic function takes flops. In this paper, we explore avenues for reducing this bound, when th…
Polynomial mechanics and optimal control
Akshay Srinivasan, Madhusudhan Venkadesan
We describe a new algorithm for trajectory optimization of mechanical systems. Our method combines pseudo-spectral methods for function approximation with variational discretizatio…