블로그

Pathmind Reinforcement Learning for Simulation webinar


Pathmind Reinforcement Learning for Simulation webinar

Pathmind is a platform that enables AnyLogic users to integrate reinforcement learning into their AnyLogic simulations. This webinar demonstrates how to set up Pathmind reinforcement learning in an AnyLogic model and train an AI policy in the Pathmind web application. We also share two example models that showcase how reinforcement learning can outperform baseline heuristics and other optimization tools.

Find out more, see the webinar recording, and learn from the example models.

AnyLogic 9 developments - connectors


AnyLogic 9 developments - connectors

If you follow our blog, you will know that we are currently working on AnyLogic 9 — a new version of the industry leading simulation tool.

Blog readers can see AnyLogic 9 in action right now. We are launching a series of articles to provide insight into some of the key changes that will come with the ninth major version of AnyLogic. Here, we will demonstrate the creation of flowcharts: in the new version, they are easier to create and edit.

The Big Book of Simulation Modeling – new chapters part 5


The Big Book of Simulation Modeling – new chapters part 5

New chapters are available for download.

The 'Big Book of Simulation Modeling, Multimethod Modeling with AnyLogic 8', is the essential text for those learning simulation modeling and AnyLogic. It is the only book to comprehensively present the three major methods in simulation modeling: agent-based, system dynamics, and discrete-event.

Suitable for new users, intermediate, and advanced, the book provides examples and step-by-step guides based on a variety of application areas. Read on and download the new chapters to read.

Pathmind Reinforcement Learning Experiment in AnyLogic 8.7.4


Pathmind Reinforcement Learning Experiment in AnyLogic 8.7.4

A new experiment in AnyLogic 8.7.4 links to Pathmind’s reinforcement learning (RL) platform, helping simulation modelers and artificial intelligence practitioners lever the synergy between simulation and AI. For large-scale and complex systems, solutions utilizing the Pathmind RL platform are outperforming well-established heuristics.

This blogpost highlights two industrial case studies from Engineering Group that use the Pathmind RL platform and introduces the integrated AnyLogic Pathmind experiment.

AnyLogic and AnyLogic Cloud updates: experiments, AGV, and the Road Traffic Library


AnyLogic and AnyLogic Cloud updates: experiments, AGV, and the Road Traffic Library

AnyLogic 8.7 and AnyLogic Cloud received updates at the end of March. Here is a quick overview of the improvements in AnyLogic 8.7.3 and AnyLogic Cloud.

New density map function. Now the map can display density not only for the current moment, but also the average for a specified period. For example, you can track the hourly change in the number of people in a store, or the average number of forklifts travelling through a workshop area per shift. To do this, in the map settings, select the Sliding window option in the Time period parameter.

Read on.

Product Delivery Reinforcement Learning


Product Delivery Reinforcement Learning

Accenture partnered with San Francisco based AI company Pathmind to investigate the potential of new reinforcement learning (RL) opportunities in simulation.

The results obtained were extremely good. The method produced a waiting time more than 4x shorter than the Nearest Agent heuristic.

In this blog, Agustin Albinati summarizes the model, introduces the three key considerations when defining the neural net, and presents the results of his team's investigations. Linked at the end of the blog is a step by step how-to with Pathmind. Read on!