EasyAgents: Reinforcement Learning for people who want to solve real-world problems

Reinforce Learning can be a game changer when you do not have training data, but are instead able to simulate an environment. Unfortunately, the theory of Reinforcement Learning is complex and the vast number of algorithms in that area adds to the burden for getting started. Easyagents takes some of the burden by making it a one-liner to run a Reinforcement Learning algorithm on your problem.

In this poster session we will both introduce the idea of Reinforcement Learning as well illustrate how Easyagents helps you with getting started with it. EasyAgents wraps reinforcement learning libraries like tf-agents or OpenAI baselines. The API is inspired by Keras and Scikit-learn and aims to get people started with reinforcement learning quickly, without having to learn any details of algorithms. We will show the diagrams and videos that are generated as default. You will also see the complete code for a small example. Easyagents is free open source can be found here: https://github.com/christianhidber/easyagents