1 code implementation • 1 Mar 2023 • Anirudh Vemula, Yuda Song, Aarti Singh, J. Andrew Bagnell, Sanjiban Choudhury
We propose a novel approach to addressing two fundamental challenges in Model-based Reinforcement Learning (MBRL): the computational expense of repeatedly finding a good policy in the learned model, and the objective mismatch between model fitting and policy computation.
1 code implementation • 17 Nov 2021 • Anirudh Vemula, Wen Sun, Maxim Likhachev, J. Andrew Bagnell
However, there is little prior theoretical work that explains the effectiveness of ILC even in the presence of large modeling errors, where optimal control methods using the misspecified model (MM) often perform poorly.
no code implementations • 13 Mar 2021 • Manash Pratim Das, Anirudh Vemula, Mayank Pathak, Sandip Aine, Maxim Likhachev
In this work, we investigate how would the robot with the help of a simulator, learn to maximize the number of boxes unloaded by each action.
1 code implementation • 21 Sep 2020 • Anirudh Vemula, J. Andrew Bagnell, Maxim Likhachev
In this paper we propose CMAX++, an approach that leverages real-world experience to improve the quality of resulting plans over successive repetitions of a robotic task.
1 code implementation • 31 Mar 2020 • Anirudh Vemula, J. Andrew Bagnell
TRON achieves this by exploiting the structure of the objective to adaptively smooth the cost function, resulting in a sequence of objectives that can be efficiently optimized.
Robotics Systems and Control Systems and Control
1 code implementation • 31 Mar 2020 • Anirudh Vemula, Wen Sun, J. Andrew Bagnell
Parameter space exploration methods with black-box optimization have recently been shown to outperform state-of-the-art approaches in continuous control reinforcement learning domains.
1 code implementation • 9 Mar 2020 • Anirudh Vemula, Yash Oza, J. Andrew Bagnell, Maxim Likhachev
In this paper, we propose CMAX an approach for interleaving planning and execution.
1 code implementation • 27 May 2019 • Wen Sun, Anirudh Vemula, Byron Boots, J. Andrew Bagnell
We design a new model-free algorithm for ILFO, Forward Adversarial Imitation Learning (FAIL), which learns a sequence of time-dependent policies by minimizing an Integral Probability Metric between the observation distributions of the expert policy and the learner.
1 code implementation • 31 Jan 2019 • Anirudh Vemula, Wen Sun, J. Andrew Bagnell
Black-box optimizers that explore in parameter space have often been shown to outperform more sophisticated action space exploration methods developed specifically for the reinforcement learning problem.
2 code implementations • 12 Oct 2017 • Anirudh Vemula, Katharina Muelling, Jean Oh
In this work, we propose Social Attention, a novel trajectory prediction model that captures the relative importance of each person when navigating in the crowd, irrespective of their proximity.
1 code implementation • 22 May 2016 • Anirudh Vemula, Katharina Muelling, Jean Oh
In this paper, we apply the idea of adaptive dimensionality to speed up path planning in dynamic environments for a robot with no assumptions on its dynamic model.