Search Results for author: Sanjiban Choudhury

Found 35 papers, 12 papers with code

Hybrid Inverse Reinforcement Learning

1 code implementation13 Feb 2024 Juntao Ren, Gokul Swamy, Zhiwei Steven Wu, J. Andrew Bagnell, Sanjiban Choudhury

In this work, we propose using hybrid RL -- training on a mixture of online and expert data -- to curtail unnecessary exploration.

Continuous Control Imitation Learning +2

Accelerating Inverse Reinforcement Learning with Expert Bootstrapping

no code implementations4 Feb 2024 David Wu, Sanjiban Choudhury

Existing inverse reinforcement learning methods (e. g. MaxEntIRL, $f$-IRL) search over candidate reward functions and solve a reinforcement learning problem in the inner loop.

Imitation Learning reinforcement-learning

The Virtues of Pessimism in Inverse Reinforcement Learning

no code implementations4 Feb 2024 David Wu, Gokul Swamy, J. Andrew Bagnell, Zhiwei Steven Wu, Sanjiban Choudhury

Inverse Reinforcement Learning (IRL) is a powerful framework for learning complex behaviors from expert demonstrations.

Offline RL reinforcement-learning +1

InteRACT: Transformer Models for Human Intent Prediction Conditioned on Robot Actions

no code implementations21 Nov 2023 Kushal Kedia, Atiksh Bhardwaj, Prithwish Dan, Sanjiban Choudhury

In collaborative human-robot manipulation, a robot must predict human intents and adapt its actions accordingly to smoothly execute tasks.

Robot Manipulation Transfer Learning

Learning Shared Safety Constraints from Multi-task Demonstrations

1 code implementation NeurIPS 2023 Konwoo Kim, Gokul Swamy, Zuxin Liu, Ding Zhao, Sanjiban Choudhury, Zhiwei Steven Wu

Regardless of the particular task we want them to perform in an environment, there are often shared safety constraints we want our agents to respect.

Continuous Control

A Game-Theoretic Framework for Joint Forecasting and Planning

1 code implementation11 Aug 2023 Kushal Kedia, Prithwish Dan, Sanjiban Choudhury

On the other hand, planning for worst-case motions leads to overtly conservative behavior and a "frozen robot".

Inverse Reinforcement Learning without Reinforcement Learning

1 code implementation26 Mar 2023 Gokul Swamy, Sanjiban Choudhury, J. Andrew Bagnell, Zhiwei Steven Wu

In this work, we demonstrate for the first time a more informed imitation learning reduction where we utilize the state distribution of the expert to alleviate the global exploration component of the RL subroutine, providing an exponential speedup in theory.

Continuous Control Imitation Learning +2

The Virtues of Laziness in Model-based RL: A Unified Objective and Algorithms

1 code implementation1 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.

Computational Efficiency Model-based Reinforcement Learning

Game-Theoretic Algorithms for Conditional Moment Matching

no code implementations19 Aug 2022 Gokul Swamy, Sanjiban Choudhury, J. Andrew Bagnell, Zhiwei Steven Wu

A variety of problems in econometrics and machine learning, including instrumental variable regression and Bellman residual minimization, can be formulated as satisfying a set of conditional moment restrictions (CMR).

Econometrics regression

Sequence Model Imitation Learning with Unobserved Contexts

1 code implementation3 Aug 2022 Gokul Swamy, Sanjiban Choudhury, J. Andrew Bagnell, Zhiwei Steven Wu

We consider imitation learning problems where the learner's ability to mimic the expert increases throughout the course of an episode as more information is revealed.

Continuous Control Imitation Learning

Minimax Optimal Online Imitation Learning via Replay Estimation

1 code implementation30 May 2022 Gokul Swamy, Nived Rajaraman, Matthew Peng, Sanjiban Choudhury, J. Andrew Bagnell, Zhiwei Steven Wu, Jiantao Jiao, Kannan Ramchandran

In the tabular setting or with linear function approximation, our meta theorem shows that the performance gap incurred by our approach achieves the optimal $\widetilde{O} \left( \min({H^{3/2}} / {N}, {H} / {\sqrt{N}} \right)$ dependency, under significantly weaker assumptions compared to prior work.

Continuous Control Imitation Learning

Causal Imitation Learning under Temporally Correlated Noise

1 code implementation2 Feb 2022 Gokul Swamy, Sanjiban Choudhury, J. Andrew Bagnell, Zhiwei Steven Wu

We develop algorithms for imitation learning from policy data that was corrupted by temporally correlated noise in expert actions.

Econometrics Imitation Learning

Leveraging Experience in Lazy Search

no code implementations10 Oct 2021 Mohak Bhardwaj, Sanjiban Choudhury, Byron Boots, Siddhartha Srinivasa

If new search problems are sufficiently similar to problems solved during training, the learned policy will choose a good edge evaluation ordering and solve the motion planning problem quickly.

Imitation Learning Motion Planning

A Critique of Strictly Batch Imitation Learning

no code implementations5 Oct 2021 Gokul Swamy, Sanjiban Choudhury, J. Andrew Bagnell, Zhiwei Steven Wu

Recent work by Jarrett et al. attempts to frame the problem of offline imitation learning (IL) as one of learning a joint energy-based model, with the hope of out-performing standard behavioral cloning.

Imitation Learning

What Would the Expert $do(\cdot)$?: Causal Imitation Learning

no code implementations29 Sep 2021 Gokul Swamy, Sanjiban Choudhury, Drew Bagnell, Steven Wu

Both approaches are able to find policies that match the result of a query to an unconfounded expert.

Imitation Learning

Learning Online from Corrective Feedback: A Meta-Algorithm for Robotics

no code implementations2 Apr 2021 Matthew Schmittle, Sanjiban Choudhury, Siddhartha S. Srinivasa

A key challenge in Imitation Learning (IL) is that optimal state actions demonstrations are difficult for the teacher to provide.

Imitation Learning

Of Moments and Matching: A Game-Theoretic Framework for Closing the Imitation Gap

2 code implementations4 Mar 2021 Gokul Swamy, Sanjiban Choudhury, J. Andrew Bagnell, Zhiwei Steven Wu

We provide a unifying view of a large family of previous imitation learning algorithms through the lens of moment matching.

Imitation Learning

Feedback in Imitation Learning: The Three Regimes of Covariate Shift

no code implementations4 Feb 2021 Jonathan Spencer, Sanjiban Choudhury, Arun Venkatraman, Brian Ziebart, J. Andrew Bagnell

The learner often comes to rely on features that are strongly predictive of decisions, but are subject to strong covariate shift.

Causal Inference Imitation Learning

Blending MPC & Value Function Approximation for Efficient Reinforcement Learning

no code implementations ICLR 2021 Mohak Bhardwaj, Sanjiban Choudhury, Byron Boots

We further propose an algorithm that changes $\lambda$ over time to reduce the dependence on MPC as our estimates of the value function improve, and test the efficacy our approach on challenging high-dimensional manipulation tasks with biased models in simulation.

Model Predictive Control reinforcement-learning +1

Autonomous Aerial Cinematography In Unstructured Environments With Learned Artistic Decision-Making

no code implementations15 Oct 2019 Rogerio Bonatti, Wenshan Wang, Cherie Ho, Aayush Ahuja, Mirko Gschwindt, Efe Camci, Erdal Kayacan, Sanjiban Choudhury, Sebastian Scherer

In this work, we address the problem in its entirety and propose a complete system for real-time aerial cinematography that for the first time combines: (1) vision-based target estimation; (2) 3D signed-distance mapping for occlusion estimation; (3) efficient trajectory optimization for long time-horizon camera motion; and (4) learning-based artistic shot selection.

Decision Making Occlusion Estimation

Leveraging Experience in Lazy Search

no code implementations16 Jul 2019 Mohak Bhardwaj, Sanjiban Choudhury, Byron Boots, Siddhartha Srinivasa

If new search problems are sufficiently similar to problems solved during training, the learned policy will choose a good edge evaluation ordering and solve the motion planning problem quickly.

Imitation Learning Motion Planning

Imitation Learning as $f$-Divergence Minimization

no code implementations30 May 2019 Liyiming Ke, Sanjiban Choudhury, Matt Barnes, Wen Sun, Gilwoo Lee, Siddhartha Srinivasa

We show that the state-of-the-art methods such as GAIL and behavior cloning, due to their choice of loss function, often incorrectly interpolate between such modes.

Imitation Learning

Towards a Robust Aerial Cinematography Platform: Localizing and Tracking Moving Targets in Unstructured Environments

no code implementations4 Apr 2019 Rogerio Bonatti, Cherie Ho, Wenshan Wang, Sanjiban Choudhury, Sebastian Scherer

In this work, we overcome such limitations and propose a complete system for aerial cinematography that combines: (1) a vision-based algorithm for target localization; (2) a real-time incremental 3D signed-distance map algorithm for occlusion and safety computation; and (3) a real-time camera motion planner that optimizes smoothness, collisions, occlusions and artistic guidelines.

Pose Estimation

Bayes-CPACE: PAC Optimal Exploration in Continuous Space Bayes-Adaptive Markov Decision Processes

no code implementations6 Oct 2018 Gilwoo Lee, Sanjiban Choudhury, Brian Hou, Siddhartha S. Srinivasa

We present the first PAC optimal algorithm for Bayes-Adaptive Markov Decision Processes (BAMDPs) in continuous state and action spaces, to the best of our knowledge.

Autonomous drone cinematographer: Using artistic principles to create smooth, safe, occlusion-free trajectories for aerial filming

no code implementations28 Aug 2018 Rogerio Bonatti, yanfu Zhang, Sanjiban Choudhury, Wenshan Wang, Sebastian Scherer

Autonomous aerial cinematography has the potential to enable automatic capture of aesthetically pleasing videos without requiring human intervention, empowering individuals with the capability of high-end film studios.

Hindsight is Only 50/50: Unsuitability of MDP based Approximate POMDP Solvers for Multi-resolution Information Gathering

no code implementations7 Apr 2018 Sankalp Arora, Sanjiban Choudhury, Sebastian Scherer

The contribution of the paper helps identify the properties of a POMDP problem for which the use of MDP based POMDP solvers is inappropriate, enabling better design choices.

Imitation Learning

Bayesian Active Edge Evaluation on Expensive Graphs

no code implementations20 Nov 2017 Sanjiban Choudhury, Siddhartha Srinivasa, Sebastian Scherer

We are interested in planning algorithms that actively infer the underlying structure of the valid configuration space during planning in order to find solutions with minimal effort.

Active Learning Motion Planning +1

Anytime Motion Planning on Large Dense Roadmaps with Expensive Edge Evaluations

1 code implementation10 Nov 2017 Shushman Choudhury, Oren Salzman, Sanjiban Choudhury, Christopher M. Dellin, Siddhartha S. Srinivasa

We propose an algorithmic framework for efficient anytime motion planning on large dense geometric roadmaps, in domains where collision checks and therefore edge evaluations are computationally expensive.

Robotics

Learning Heuristic Search via Imitation

1 code implementation10 Jul 2017 Mohak Bhardwaj, Sanjiban Choudhury, Sebastian Scherer

In this paper, we do so by training a heuristic policy that maps the partial information from the search to decide which node of the search tree to expand.

Motion Planning valid

Near-Optimal Edge Evaluation in Explicit Generalized Binomial Graphs

1 code implementation NeurIPS 2017 Sanjiban Choudhury, Shervin Javdani, Siddhartha Srinivasa, Sebastian Scherer

By leveraging this property, we are able to significantly reduce computational complexity from exponential to linear in the number of edges.

Robotics

Learning to Gather Information via Imitation

no code implementations13 Nov 2016 Sanjiban Choudhury, Ashish Kapoor, Gireeja Ranade, Debadeepta Dey

The budgeted information gathering problem - where a robot with a fixed fuel budget is required to maximize the amount of information gathered from the world - appears in practice across a wide range of applications in autonomous exploration and inspection with mobile robots.

Imitation Learning

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