Search Results for author: Anirudha Majumdar

Found 25 papers, 12 papers with code

Fundamental Performance Limits for Sensor-Based Robot Control and Policy Learning

1 code implementation31 Jan 2022 Anirudha Majumdar, Vincent Pacelli

Our goal is to develop theory and algorithms for establishing fundamental limits on performance for a given task imposed by a robot's sensors.

Decision Making

Learning Provably Robust Motion Planners Using Funnel Libraries

no code implementations16 Nov 2021 Ali Ekin Gurgen, Anirudha Majumdar, Sushant Veer

This paper presents an approach for learning motion planners that are accompanied with probabilistic guarantees of success on new environments that hold uniformly for any disturbance to the robot's dynamics within an admissible set.

Generalization Bounds

Stronger Generalization Guarantees for Robot Learning by Combining Generative Models and Real-World Data

no code implementations16 Nov 2021 Abhinav Agarwal, Sushant Veer, Allen Z. Ren, Anirudha Majumdar

The key idea behind our approach is to utilize the generative model in order to implicitly specify a prior over policies.

Distributionally Robust Policy Learning via Adversarial Environment Generation

1 code implementation13 Jul 2021 Allen Z. Ren, Anirudha Majumdar

Our goal is to train control policies that generalize well to unseen environments.

Task-Driven Detection of Distribution Shifts with Statistical Guarantees for Robot Learning

1 code implementation25 Jun 2021 Alec Farid, Sushant Veer, Divyanshu Pachisia, Anirudha Majumdar

Our goal is to perform out-of-distribution (OOD) detection, i. e., to detect when a robot is operating in environments that are drawn from a different distribution than the environments used to train the robot.

OOD Detection Out-of-Distribution Detection

A Regret Minimization Approach to Iterative Learning Control

no code implementations26 Feb 2021 Naman Agarwal, Elad Hazan, Anirudha Majumdar, Karan Singh

We consider the setting of iterative learning control, or model-based policy learning in the presence of uncertain, time-varying dynamics.

Deluca -- A Differentiable Control Library: Environments, Methods, and Benchmarking

1 code implementation19 Feb 2021 Paula Gradu, John Hallman, Daniel Suo, Alex Yu, Naman Agarwal, Udaya Ghai, Karan Singh, Cyril Zhang, Anirudha Majumdar, Elad Hazan

We present an open-source library of natively differentiable physics and robotics environments, accompanied by gradient-based control methods and a benchmark-ing suite.

OpenAI Gym

Generating Adversarial Disturbances for Controller Verification

no code implementations12 Dec 2020 Udaya Ghai, David Snyder, Anirudha Majumdar, Elad Hazan

We consider the problem of generating maximally adversarial disturbances for a given controller assuming only blackbox access to it.

online learning

LagNetViP: A Lagrangian Neural Network for Video Prediction

no code implementations24 Oct 2020 Christine Allen-Blanchette, Sushant Veer, Anirudha Majumdar, Naomi Ehrich Leonard

In this paper, we introduce a video prediction model where the equations of motion are explicitly constructed from learned representations of the underlying physical quantities.

Acrobot Video Prediction

Learning to Actively Reduce Memory Requirements for Robot Control Tasks

1 code implementation17 Aug 2020 Meghan Booker, Anirudha Majumdar

State-of-the-art approaches for controlling robots often use memory representations that are excessively rich for the task or rely on hand-crafted tricks for memory efficiency.

Generalization Guarantees for Imitation Learning

2 code implementations5 Aug 2020 Allen Z. Ren, Sushant Veer, Anirudha Majumdar

Control policies from imitation learning can often fail to generalize to novel environments due to imperfect demonstrations or the inability of imitation learning algorithms to accurately infer the expert's policies.

Generalization Bounds Imitation Learning

CoNES: Convex Natural Evolutionary Strategies

no code implementations16 Jul 2020 Sushant Veer, Anirudha Majumdar

We present a novel algorithm -- convex natural evolutionary strategies (CoNES) -- for optimizing high-dimensional blackbox functions by leveraging tools from convex optimization and information geometry.

reinforcement-learning

Invariant Policy Optimization: Towards Stronger Generalization in Reinforcement Learning

1 code implementation1 Jun 2020 Anoopkumar Sonar, Vincent Pacelli, Anirudha Majumdar

A fundamental challenge in reinforcement learning is to learn policies that generalize beyond the operating domains experienced during training.

Policy Gradient Methods reinforcement-learning

Probably Approximately Correct Vision-Based Planning using Motion Primitives

1 code implementation28 Feb 2020 Sushant Veer, Anirudha Majumdar

This paper presents an approach for learning vision-based planners that provably generalize to novel environments (i. e., environments unseen during training).

Learning Task-Driven Control Policies via Information Bottlenecks

no code implementations4 Feb 2020 Vincent Pacelli, Anirudha Majumdar

Standard reinforcement learning algorithms typically produce policies that tightly couple control actions to the entirety of the system's state and rich sensor observations.

reinforcement-learning

A Survey of Recent Scalability Improvements for Semidefinite Programming with Applications in Machine Learning, Control, and Robotics

no code implementations14 Aug 2019 Anirudha Majumdar, Georgina Hall, Amir Ali Ahmadi

Historically, scalability has been a major challenge to the successful application of semidefinite programming in fields such as machine learning, control, and robotics.

Task-Driven Estimation and Control via Information Bottlenecks

1 code implementation20 Sep 2018 Vincent Pacelli, Anirudha Majumdar

We propose novel iterative algorithms for automatically synthesizing (offline) a task-driven representation (given in terms of a set of task-relevant variables (TRVs)) and a performant control policy that is a function of the TRVs.

Optimization and Control Robotics Systems and Control

PAC-Bayes Control: Learning Policies that Provably Generalize to Novel Environments

1 code implementation11 Jun 2018 Anirudha Majumdar, Alec Farid, Anoopkumar Sonar

The key technical idea behind our approach is to leverage tools from generalization theory in machine learning by exploiting a precise analogy (which we present in the form of a reduction) between generalization of control policies to novel environments and generalization of hypotheses in the supervised learning setting.

Risk-sensitive Inverse Reinforcement Learning via Semi- and Non-Parametric Methods

1 code implementation28 Nov 2017 Sumeet Singh, Jonathan Lacotte, Anirudha Majumdar, Marco Pavone

The literature on Inverse Reinforcement Learning (IRL) typically assumes that humans take actions in order to minimize the expected value of a cost function, i. e., that humans are risk neutral.

Decision Making reinforcement-learning

How Should a Robot Assess Risk? Towards an Axiomatic Theory of Risk in Robotics

no code implementations30 Oct 2017 Anirudha Majumdar, Marco Pavone

We discuss general representation theorems that precisely characterize the class of metrics that satisfy these axioms (referred to as distortion risk metrics), and provide instantiations that can be used in applications.

Decision Making

Response to "Counterexample to global convergence of DSOS and SDSOS hierarchies"

no code implementations9 Oct 2017 Amir Ali Ahmadi, Anirudha Majumdar

In a recent note [8], the author provides a counterexample to the global convergence of what his work refers to as "the DSOS and SDSOS hierarchies" for polynomial optimization problems (POPs) and purports that this refutes claims in our extended abstract [4] and slides in [3].

DSOS and SDSOS Optimization: More Tractable Alternatives to Sum of Squares and Semidefinite Optimization

no code implementations8 Jun 2017 Amir Ali Ahmadi, Anirudha Majumdar

The reliance of this technique on large-scale semidefinite programs however, has limited the scale of problems to which it can be applied.

Funnel Libraries for Real-Time Robust Feedback Motion Planning

no code implementations15 Jan 2016 Anirudha Majumdar, Russ Tedrake

We consider the problem of generating motion plans for a robot that are guaranteed to succeed despite uncertainty in the environment, parametric model uncertainty, and disturbances.

Motion Planning

Cannot find the paper you are looking for? You can Submit a new open access paper.