Search Results for author: Shlomo Zilberstein

Found 26 papers, 3 papers with code

RL$^3$: Boosting Meta Reinforcement Learning via RL inside RL$^2$

1 code implementation28 Jun 2023 Abhinav Bhatia, Samer B. Nashed, Shlomo Zilberstein

Meta reinforcement learning (meta-RL) methods such as RL$^2$ have emerged as promising approaches for learning data-efficient RL algorithms tailored to a given task distribution.

Meta Reinforcement Learning reinforcement-learning

Adaptive Rollout Length for Model-Based RL Using Model-Free Deep RL

no code implementations6 Jun 2022 Abhinav Bhatia, Philip S. Thomas, Shlomo Zilberstein

Model-based reinforcement learning promises to learn an optimal policy from fewer interactions with the environment compared to model-free reinforcement learning by learning an intermediate model of the environment in order to predict future interactions.

Decision Making Model-based Reinforcement Learning +2

Dense Crowd Flow-Informed Path Planning

no code implementations1 Jun 2022 Emily Pruc, Shlomo Zilberstein, Joydeep Biswas

In the case of pedestrian-unaware mobile robots this desire for safety leads to the freezing robot problem, where a robot confronted with a large dynamic group of obstacles (such as a crowd of pedestrians) would determine all forward navigation unsafe causing the robot to stop in place.


Causal Explanations for Sequential Decision Making Under Uncertainty

no code implementations30 May 2022 Samer B. Nashed, Saaduddin Mahmud, Claudia V. Goldman, Shlomo Zilberstein

We introduce a novel framework for causal explanations of stochastic, sequential decision-making systems built on the well-studied structural causal model paradigm for causal reasoning.

Causal Inference Decision Making +1

Competence-Aware Path Planning via Introspective Perception

no code implementations28 Sep 2021 Sadegh Rabiee, Connor Basich, Kyle Hollins Wray, Shlomo Zilberstein, Joydeep Biswas

First, perception errors are learned in a model-free and location-agnostic setting via introspective perception prior to deployment in novel environments.

Agent-aware State Estimation in Autonomous Vehicles

1 code implementation1 Aug 2021 Shane Parr, Ishan Khatri, Justin Svegliato, Shlomo Zilberstein

Autonomous systems often operate in environments where the behavior of multiple agents is coordinated by a shared global state.

Autonomous Vehicles

Mitigating Negative Side Effects via Environment Shaping

no code implementations13 Feb 2021 Sandhya Saisubramanian, Shlomo Zilberstein

The human shapes the environment through minor reconfiguration actions so as to mitigate the impacts of the agent's side effects, without affecting the agent's ability to complete its assigned task.

Learning to Generate Fair Clusters from Demonstrations

no code implementations8 Feb 2021 Sainyam Galhotra, Sandhya Saisubramanian, Shlomo Zilberstein

Empirical evaluation on three real-world datasets demonstrates the effectiveness of our approach in quickly identifying the underlying fairness and interpretability constraints, which are then used to generate fair and interpretable clusters.

Clustering Fairness

Helpfulness as a Key Metric of Human-Robot Collaboration

no code implementations10 Oct 2020 Richard G. Freedman, Steven J. Levine, Brian C. Williams, Shlomo Zilberstein

As robotic teammates become more common in society, people will assess the robots' roles in their interactions along many dimensions.

Decision Making

Avoiding Negative Side Effects due to Incomplete Knowledge of AI Systems

no code implementations24 Aug 2020 Sandhya Saisubramanian, Shlomo Zilberstein, Ece Kamar

Learning to recognize and avoid such negative side effects of an agent's actions is critical to improve the safety and reliability of autonomous systems.

Improving Competence for Reliable Autonomy

no code implementations23 Jul 2020 Connor Basich, Justin Svegliato, Kyle Hollins Wray, Stefan J. Witwicki, Shlomo Zilberstein

Given the complexity of real-world, unstructured domains, it is often impossible or impractical to design models that include every feature needed to handle all possible scenarios that an autonomous system may encounter.

Learning to Optimize Autonomy in Competence-Aware Systems

no code implementations17 Mar 2020 Connor Basich, Justin Svegliato, Kyle Hollins Wray, Stefan Witwicki, Joydeep Biswas, Shlomo Zilberstein

Interest in semi-autonomous systems (SAS) is growing rapidly as a paradigm to deploy autonomous systems in domains that require occasional reliance on humans.

Autonomous Driving

Balancing the Tradeoff Between Clustering Value and Interpretability

1 code implementation17 Dec 2019 Sandhya Saisubramanian, Sainyam Galhotra, Shlomo Zilberstein

The interpretability of the clusters is complemented by generating simple explanations denoting the feature values of the nodes in the clusters, using frequent pattern mining.

Clustering Graph Clustering

Responsive Planning and Recognition for Closed-Loop Interaction

no code implementations13 Sep 2019 Richard G. Freedman, Yi Ren Fung, Roman Ganchin, Shlomo Zilberstein

Many intelligent systems currently interact with others using at least one of fixed communication inputs or preset responses, resulting in rigid interaction experiences and extensive efforts developing a variety of scenarios for the system.

Minimizing the Negative Side Effects of Planning with Reduced Models

no code implementations22 May 2019 Sandhya Saisubramanian, Shlomo Zilberstein

To that end, we propose planning using a portfolio of reduced models, a planning paradigm that minimizes the negative side effects of planning using reduced models by alternating between different outcome selection approaches.

Lexicographically Ordered Multi-Objective Clustering

no code implementations2 Mar 2019 Sainyam Galhotra, Sandhya Saisubramanian, Shlomo Zilberstein

We introduce a rich model for multi-objective clustering with lexicographic ordering over objectives and a slack.


Planning in Stochastic Environments with Goal Uncertainty

no code implementations18 Oct 2018 Sandhya Saisubramanian, Kyle Hollins Wray, Luis Pineda, Shlomo Zilberstein

The framework extends the stochastic shortest path (SSP) model to dynamic environments in which it is impossible to determine the exact goal states ahead of plan execution.

Decision Making

An Anytime Algorithm for Task and Motion MDPs

no code implementations16 Feb 2018 Siddharth Srivastava, Nishant Desai, Richard Freedman, Shlomo Zilberstein

We present a new approach where the high-level decision problem occurs in a stochastic setting and can be modeled as a Markov decision process.

Decision Making Motion Planning +1

Generalizing the Role of Determinization in Probabilistic Planning

no code implementations21 May 2017 Luis Pineda, Shlomo Zilberstein

The stochastic shortest path problem (SSP) is a highly expressive model for probabilistic planning.

Robust Optimization for Tree-Structured Stochastic Network Design

no code implementations1 Dec 2016 Xiaojian Wu, Akshat Kumar, Daniel Sheldon, Shlomo Zilberstein

We therefore address the robust river network design problem where the goal is to optimize river connectivity for fish movement by removing barriers.

Policy Iteration for Decentralized Control of Markov Decision Processes

no code implementations15 Jan 2014 Daniel S. Bernstein, Christopher Amato, Eric A. Hansen, Shlomo Zilberstein

The main contribution of this paper is an optimal policy iteration algorithm for solving DEC-POMDPs.

A Bilinear Programming Approach for Multiagent Planning

no code implementations15 Jan 2014 Marek Petrik, Shlomo Zilberstein

Because the algorithm is formulated for bilinear programs, it is more general and simpler to implement.

Dimensionality Reduction

MAP Estimation for Graphical Models by Likelihood Maximization

no code implementations NeurIPS 2010 Akshat Kumar, Shlomo Zilberstein

We experiment on the real-world protein design dataset and show that EM's convergence rate is significantly higher than the previous LP relaxation based approach MPLP.

Protein Design

Robust Value Function Approximation Using Bilinear Programming

no code implementations NeurIPS 2009 Marek Petrik, Shlomo Zilberstein

Existing value function approximation methods have been successfully used in many applications, but they often lack useful a priori error bounds.

Complexity of Decentralized Control: Special Cases

no code implementations NeurIPS 2009 Martin Allen, Shlomo Zilberstein

The worst-case complexity of general decentralized POMDPs, which are equivalent to partially observable stochastic games (POSGs) is very high, both for the cooperative and competitive cases.

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