1 citations · 2 across the 7 of their papers we have counts for
9 papers
On-Line Policy Iteration with Trajectory-Driven Policy Generation
Yuchao Li, Fei Chen, Yingke Li +2
We consider deterministic finite-horizon optimal control problems with a fixed initial state. We introduce an on-line policy iteration method, which, starting from a given policy,…
Model Predictive Control For Trade Execution
Thomas P. McAuliffe, Samuel Liew, Yuchao Li +7
We address the problem of executing large client orders in continuous double-auction markets under time and liquidity constraints. We propose a model predictive control (MPC) frame…
Feature-Based Belief Aggregation for Partially Observable Markov Decision Problems
Yuchao Li, Kim Hammar, Dimitri Bertsekas
We consider a finite-state partially observable Markov decision problem (POMDP) with an infinite horizon and a discounted cost, and we propose a new method for computing a cost fun…
Adaptive Network Security Policies via Belief Aggregation and Rollout
Kim Hammar, Yuchao Li, Tansu Alpcan +2
Evolving security vulnerabilities and shifting operational conditions require frequent updates to network security policies. These updates include adjustments to incident response…
An Error Bound for Aggregation in Approximate Dynamic Programming
Yuchao Li, Dimitri Bertsekas
We consider a general aggregation framework for discounted finite-state infinite horizon dynamic programming (DP) problems. It defines an aggregate problem whose optimal cost funct…
Semilinear Dynamic Programming: Analysis, Algorithms, and Certainty Equivalence Properties
Yuchao Li, Dimitri Bertsekas
We consider a broad class of dynamic programming (DP) problems that involve a partially linear structure and some positivity properties in their system equation and cost function.…
Superior Computer Chess with Model Predictive Control, Reinforcement Learning, and Rollout
Atharva Gundawar, Yuchao Li, Dimitri Bertsekas
In this paper we apply model predictive control (MPC), rollout, and reinforcement learning (RL) methodologies to computer chess. We introduce a new architecture for move selection,…
An Approximate Dynamic Programming Framework for Occlusion-Robust Multi-Object Tracking
Pratyusha Musunuru, Yuchao Li, Jamison Weber +1
In this work, we consider data association problems involving multi-object tracking (MOT). In particular, we address the challenges arising from object occlusions. We propose a fra…
Most Likely Sequence Generation for -Grams, Transformers, HMMs, and Markov Chains, by Using Rollout Algorithms
Yuchao Li, Dimitri Bertsekas
In this paper we consider a transformer with an -gram structure, such as the one underlying ChatGPT. The transformer provides next word probabilities, which can be used to gener…