Picture for Shankar Sastry

Shankar Sastry

Decentralized Learning in General-sum Markov Games

Add code
Sep 06, 2024
Viaarxiv icon

Hacking Predictors Means Hacking Cars: Using Sensitivity Analysis to Identify Trajectory Prediction Vulnerabilities for Autonomous Driving Security

Add code
Jan 18, 2024
Viaarxiv icon

Markov $α$-Potential Games: Equilibrium Approximation and Regret Analysis

Add code
May 24, 2023
Viaarxiv icon

Representation Learning via Manifold Flattening and Reconstruction

Add code
May 12, 2023
Viaarxiv icon

Towards Dynamic Causal Discovery with Rare Events: A Nonparametric Conditional Independence Test

Add code
Dec 01, 2022
Viaarxiv icon

Lyapunov Design for Robust and Efficient Robotic Reinforcement Learning

Add code
Aug 13, 2022
Figure 1 for Lyapunov Design for Robust and Efficient Robotic Reinforcement Learning
Figure 2 for Lyapunov Design for Robust and Efficient Robotic Reinforcement Learning
Figure 3 for Lyapunov Design for Robust and Efficient Robotic Reinforcement Learning
Figure 4 for Lyapunov Design for Robust and Efficient Robotic Reinforcement Learning
Viaarxiv icon

Decentralized, Communication- and Coordination-free Learning in Structured Matching Markets

Add code
Jun 06, 2022
Figure 1 for Decentralized, Communication- and Coordination-free Learning in Structured Matching Markets
Figure 2 for Decentralized, Communication- and Coordination-free Learning in Structured Matching Markets
Figure 3 for Decentralized, Communication- and Coordination-free Learning in Structured Matching Markets
Figure 4 for Decentralized, Communication- and Coordination-free Learning in Structured Matching Markets
Viaarxiv icon

Independent and Decentralized Learning in Markov Potential Games

Add code
May 31, 2022
Figure 1 for Independent and Decentralized Learning in Markov Potential Games
Figure 2 for Independent and Decentralized Learning in Markov Potential Games
Figure 3 for Independent and Decentralized Learning in Markov Potential Games
Viaarxiv icon

Residual Networks: Lyapunov Stability and Convex Decomposition

Add code
Mar 22, 2018
Figure 1 for Residual Networks: Lyapunov Stability and Convex Decomposition
Figure 2 for Residual Networks: Lyapunov Stability and Convex Decomposition
Figure 3 for Residual Networks: Lyapunov Stability and Convex Decomposition
Figure 4 for Residual Networks: Lyapunov Stability and Convex Decomposition
Viaarxiv icon

Surprise-Based Intrinsic Motivation for Deep Reinforcement Learning

Add code
Mar 06, 2017
Figure 1 for Surprise-Based Intrinsic Motivation for Deep Reinforcement Learning
Figure 2 for Surprise-Based Intrinsic Motivation for Deep Reinforcement Learning
Figure 3 for Surprise-Based Intrinsic Motivation for Deep Reinforcement Learning
Figure 4 for Surprise-Based Intrinsic Motivation for Deep Reinforcement Learning
Viaarxiv icon