Picture for Dimitri Bertsekas

Dimitri Bertsekas

An Approximate Dynamic Programming Framework for Occlusion-Robust Multi-Object Tracking

Add code
May 24, 2024
Viaarxiv icon

Most Likely Sequence Generation for $n$-Grams, Transformers, HMMs, and Markov Chains, by Using Rollout Algorithms

Add code
Mar 19, 2024
Viaarxiv icon

Approximate Multiagent Reinforcement Learning for On-Demand Urban Mobility Problem on a Large Map (extended version)

Add code
Nov 02, 2023
Viaarxiv icon

Rollout Algorithms and Approximate Dynamic Programming for Bayesian Optimization and Sequential Estimation

Add code
Dec 29, 2022
Figure 1 for Rollout Algorithms and Approximate Dynamic Programming for Bayesian Optimization and Sequential Estimation
Figure 2 for Rollout Algorithms and Approximate Dynamic Programming for Bayesian Optimization and Sequential Estimation
Figure 3 for Rollout Algorithms and Approximate Dynamic Programming for Bayesian Optimization and Sequential Estimation
Viaarxiv icon

Reinforcement Learning Methods for Wordle: A POMDP/Adaptive Control Approach

Add code
Nov 29, 2022
Figure 1 for Reinforcement Learning Methods for Wordle: A POMDP/Adaptive Control Approach
Figure 2 for Reinforcement Learning Methods for Wordle: A POMDP/Adaptive Control Approach
Figure 3 for Reinforcement Learning Methods for Wordle: A POMDP/Adaptive Control Approach
Figure 4 for Reinforcement Learning Methods for Wordle: A POMDP/Adaptive Control Approach
Viaarxiv icon

Multiagent Reinforcement Learning for Autonomous Routing and Pickup Problem with Adaptation to Variable Demand

Add code
Nov 28, 2022
Figure 1 for Multiagent Reinforcement Learning for Autonomous Routing and Pickup Problem with Adaptation to Variable Demand
Figure 2 for Multiagent Reinforcement Learning for Autonomous Routing and Pickup Problem with Adaptation to Variable Demand
Figure 3 for Multiagent Reinforcement Learning for Autonomous Routing and Pickup Problem with Adaptation to Variable Demand
Figure 4 for Multiagent Reinforcement Learning for Autonomous Routing and Pickup Problem with Adaptation to Variable Demand
Viaarxiv icon

New Auction Algorithms for Path Planning, Network Transport, and Reinforcement Learning

Add code
Jul 19, 2022
Figure 1 for New Auction Algorithms for Path Planning, Network Transport, and Reinforcement Learning
Figure 2 for New Auction Algorithms for Path Planning, Network Transport, and Reinforcement Learning
Figure 3 for New Auction Algorithms for Path Planning, Network Transport, and Reinforcement Learning
Figure 4 for New Auction Algorithms for Path Planning, Network Transport, and Reinforcement Learning
Viaarxiv icon

Lessons from AlphaZero for Optimal, Model Predictive, and Adaptive Control

Add code
Aug 20, 2021
Figure 1 for Lessons from AlphaZero for Optimal, Model Predictive, and Adaptive Control
Figure 2 for Lessons from AlphaZero for Optimal, Model Predictive, and Adaptive Control
Figure 3 for Lessons from AlphaZero for Optimal, Model Predictive, and Adaptive Control
Figure 4 for Lessons from AlphaZero for Optimal, Model Predictive, and Adaptive Control
Viaarxiv icon

On-Line Policy Iteration for Infinite Horizon Dynamic Programming

Add code
Jun 01, 2021
Viaarxiv icon

Multiagent Rollout and Policy Iteration for POMDP with Application to Multi-Robot Repair Problems

Add code
Nov 09, 2020
Figure 1 for Multiagent Rollout and Policy Iteration for POMDP with Application to Multi-Robot Repair Problems
Figure 2 for Multiagent Rollout and Policy Iteration for POMDP with Application to Multi-Robot Repair Problems
Figure 3 for Multiagent Rollout and Policy Iteration for POMDP with Application to Multi-Robot Repair Problems
Figure 4 for Multiagent Rollout and Policy Iteration for POMDP with Application to Multi-Robot Repair Problems
Viaarxiv icon