Search Results for author:
Found 14 papers, 1 papers with code
Most Likely Sequence Generation for $n$-Grams, Transformers, HMMs, and Markov Chains, by Using Rollout Algorithms
We consider methods for computing word sequences that are highly likely, based on these probabilities.
Approximate Multiagent Reinforcement Learning for On-Demand Urban Mobility Problem on a Large Map (extended version)
We provide two main theoretical results: 1) characterize the number of taxis $m$ that is sufficient for IA to be stable; 2) derive a necessary condition on $m$ to maintain stability for IA as time goes to infinity.
Rollout Algorithms and Approximate Dynamic Programming for Bayesian Optimization and Sequential Estimation
We provide a unifying approximate dynamic programming framework that applies to a broad variety of problems involving sequential estimation.
Multiagent Reinforcement Learning for Autonomous Routing and Pickup Problem with Adaptation to Variable Demand
We propose a mechanism for switching the originally trained offline approximation when the current demand is outside the original validity region.
Reinforcement Learning Methods for Wordle: A POMDP/Adaptive Control Approach
In this paper we address the solution of the popular Wordle puzzle, using new reinforcement learning methods, which apply more generally to adaptive control of dynamic systems and to classes of Partially Observable Markov Decision Process (POMDP) problems.
New Auction Algorithms for Path Planning, Network Transport, and Reinforcement Learning
We consider some classical optimization problems in path planning and network transport, and we introduce new auction-based algorithms for their optimal and suboptimal solution.
Lessons from AlphaZero for Optimal, Model Predictive, and Adaptive Control
In this paper we aim to provide analysis and insights (often based on visualization), which explain the beneficial effects of on-line decision making on top of off-line training.
On-Line Policy Iteration for Infinite Horizon Dynamic Programming
This allows the continuous updating/improvement of the current policy, thus resulting in a form of on-line PI that incorporates the improved controls into the current policy as new states and controls are generated.
Multiagent Rollout and Policy Iteration for POMDP with Application to Multi-Robot Repair Problems
Our methods specifically address the computational challenges of partially observable multiagent problems.
Multiagent Value Iteration Algorithms in Dynamic Programming and Reinforcement Learning
In this paper, this result is extended to value iteration and optimistic versions of policy iteration, as well as to more general DP problems where the Bellman operator is a contraction mapping, such as stochastic shortest path problems with all policies being proper.
Constrained Multiagent Rollout and Multidimensional Assignment with the Auction Algorithm
Under suitable assumptions, we show that if the base heuristic produces a feasible solution, the rollout algorithm has a cost improvement property: it produces a feasible solution, whose cost is no worse than the base heuristic's cost.
Reinforcement Learning for POMDP: Partitioned Rollout and Policy Iteration with Application to Autonomous Sequential Repair Problems
In this paper we consider infinite horizon discounted dynamic programming problems with finite state and control spaces, and partial state observations.
Biased Aggregation, Rollout, and Enhanced Policy Improvement for Reinforcement Learning
When $V$ is equal to the cost function $J_{\mu}$ of some known policy $\mu$ and there is only one aggregate state, our scheme is equivalent to the rollout algorithm based on $\mu$ (i. e., the result of a single policy improvement starting with the policy $\mu$).
Multiagent Rollout Algorithms and Reinforcement Learning
The amount of local computation required at every stage by each agent is independent of the number of agents, while the amount of total computation (over all agents) grows linearly with the number of agents.
