scispace - formally typeset
A

Aravind Rajeswaran

Researcher at University of Washington

Publications -  57
Citations -  4470

Aravind Rajeswaran is an academic researcher from University of Washington. The author has contributed to research in topics: Reinforcement learning & Computer science. The author has an hindex of 23, co-authored 44 publications receiving 2426 citations. Previous affiliations of Aravind Rajeswaran include Indian Institute of Technology Madras.

Papers
More filters
Posted Content

Decision Transformer: Reinforcement Learning via Sequence Modeling

TL;DR: Despite its simplicity, Decision Transformer matches or exceeds the performance of state-of-the-art model-free offline RL baselines on Atari, OpenAI Gym, and Key-to-Door tasks.
Posted Content

Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations

TL;DR: In this paper, a model-free DRL can effectively scale up to complex dexterous manipulation tasks with a high-dimensional 24-DoF hand, and solve them from scratch in simulated experiments.
Proceedings Article

Meta-Learning with Implicit Gradients

TL;DR: Theoretically, it is proved that implicit MAML can compute accurate meta-gradients with a memory footprint that is, up to small constant factors, no more than that which is required to compute a single inner loop gradient and at no overall increase in the total computational cost.
Posted Content

Meta-Learning with Implicit Gradients

TL;DR: The implicit MAML algorithm as discussed by the authors decouples the meta-gradient computation from the choice of inner-loop optimizer and can gracefully handle many gradient steps without vanishing gradients or memory constraints.