Skip to main content

Questions tagged [reinforcement-learning]

For questions related to reinforcement learning, a type of machine learning algorithm in which a computerized agent learns through experimentation how to optimize its actions in an environment to maximize its reward.

Filter by
Sorted by
Tagged with
24 votes
4 answers

What are the tradeoffs between "exact" and Reinforcement Learning methods for solving optimization problems

Exact methods, e.g., models that utilize an MIP approach with a specified objective and constraints, have advantages like the following: Using off the shelf solvers Optimality gap provability ...
fhk's user avatar
  • 1,069
19 votes
1 answer

Deep Reinforcement Learning for General Purpose Optimization

Recently, I attended a very nice talk given by someone at the place I work about applying Deep Reinforcement Learning (DRL) for a design optimization problem. It was particularly interesting to me ...
chupa_kabra's user avatar
  • 1,485
18 votes
3 answers

What is the connection of Operations Research and Reinforcement Learning?

I know that Markov Chains and Markov Decision Processes have been studied in the OR community too. But, I was wondering what is the relationship of Operations Research (OR) and Reinforcement Learning (...
Afshin Oroojlooy's user avatar
14 votes
4 answers

Online Education for OR and Developing Decision Support Systems

I am looking for educational programmes which can be conducted online, such as full MSc., degree certificates, postgraduate courses/modules, MOOCs. Topics I am looking for are on advanced ...
Aks's user avatar
  • 317
14 votes
2 answers

Suggestion of some courses in sequential decision making

I am studying about sequential decision making and I am willing to know if there is any course which is recorded and is publically available covering topics in dynamic programming (DP), reinforcement ...
Amin's user avatar
  • 2,160
8 votes
2 answers

Status of reinforcement learning for (mixed) integer programming?

I'm curious whether Reinforcement Learning is or will become the state of the art solution for (mixed) integer programming. I imagine that this would fall under the umbrella of heuristics. Companies ...
jbuddy_13's user avatar
  • 551
6 votes
1 answer

When was the exploration and exploitation tradeoff first mentioned in literature?

I've recently been exploring Reinforcement Learning (RL) methods in my work and the exploration-exploitation dilemma is always mentioned. It almost feels like the exploration-exploitation dilemma ...
jkschin's user avatar
  • 365
5 votes
0 answers

Convergence of an approximate DP for a stochastic shortest path problem

I'm new to the field of sequential decision making. I got intrigued by a stochastic shortest path problem, described in Chapter 5 of this book by W. Powell. Consider the following stochastic shortest ...
Joris Kinable's user avatar
3 votes
2 answers

Can we use reinforcement learning and convex optimization to solve an optimization problem?

For an optimization problem, there are multiple-type variables should be optimized. Can we use the convex optimization method to solve a subproblem of partial variables, and then, with the obtained ...
qinqinxiaoguai's user avatar
3 votes
1 answer

Can Deep RL be used to find optimal division point in an application?

I need to optimise the end-to-end latency for a multi-service application while distributing it on multiple devices. The application is a series of services interconnected to each other. The goal is ...
user1566490's user avatar
2 votes
2 answers

AI based Optimization

I will start an optimization project in a bottlenecked bottling and filling line of a brewery. The goal is to produce the maximum number of cans and bottles of beer with minimum downtime and slowdowns....
alpers7's user avatar
  • 29
2 votes
1 answer

Determining which choice strategy (epsilon-greedy, softmax, UCB, etc.) fits participant behavior in a multi armed bandit study

I'm trying to estimate the effect of personality on exploration behavior in multi armed bandit problems. My current approach is to identify the choice strategy that most accurately fits the behavior ...
Fischdose's user avatar
2 votes
1 answer

Understanding MDP's Dual Linear Program

I'm trying to understand a proof in Puterman'05 (Markov Decision Processes: Discrete Stochastic Systems). My question is within Theorem 6.9.1 pertaining to the equivalence of solutions to the primal (...
Max's user avatar
  • 23
2 votes
0 answers

Optimal spending of cash problem

I have often wondered whether there is an optimal way to spend cash denominations. For example: Suppose that Bob needs to pay Jill \$5, Jane \$10, Billy \$3.50 and John \$45.75. Furthermore suppose ...
Benjamin Beer's user avatar
1 vote
0 answers

Multicollinearity w.r.t decisions in optimal control/reinforcement learning learning/resource allocation problem

Consider the following optimization/control problem: We aim to maximize the cumulative reward $R$ during the horizon $H$ by every day allocating a portion of total budget $B$ to our two different ...
chrisrichardsson's user avatar
1 vote
0 answers

Rule set optimization

My question is with regards to a research topic: Rule-set optimization []. If one were to use rule-set optimization for fraud detection. ...
Ishaan's user avatar
  • 139
0 votes
0 answers

Reinforcement learning for a Assignment Problem

I was just wondering if it is technically possible to solve a general assignment problem using reinforcement learning? You could use the inverted objective function as a reward function, right? Have ...
marvelfab12's user avatar
0 votes
0 answers

Resource allocation problem - RL or stochastic optimization?

I am currently working on a resource allocation problem and I am uncertain about which field of stochastic optimization and reinforcement learning encompasses this particular problem. The objective is ...
liam urate's user avatar
0 votes
0 answers

Creating a simple class in python for doing simulation of MDP

I am currently learning Python and doing object-oriented programming. I am trying to create a simulation for MDP. My problem statement is: "I have four stages of process. Each stage has two ...
Margi Shah's user avatar