no code implementations • 3 Mar 2024 • Pulkit Katdare, Anant Joshi, Katherine Driggs-Campbell
In this work, we argue that this residual term is significant and correcting for it could potentially improve sample-complexity of reinforcement learning methods.
no code implementations • 4 Sep 2023 • Pulkit Katdare, Nan Jiang, Katherine Driggs-Campbell
This paper proposes a new approach to evaluate the real-world performance of agent policies prior to deploying them in the real world.
1 code implementation • 21 Dec 2021 • Pulkit Katdare, Shuijing Liu, Katherine Driggs-Campbell
We also show that the our method is able to estimate performance of a 7 DOF robotic arm using the simulator and remotely collected data from the robot in the real world.