Taking a Walk in the OpenAI Gym: Using Decision Transformer to Power Reinforcement Learning

Author(s): Brent Larzalere

Originally published on Towards AI.

Perform Deep Reinforcement Learning using the Decision Transformer

deepmind-lISkvdgfLEk-unsplash

This article will describe how to use a decision transformer model to perform deep reinforcement learning in the OpenAI gym. PyTorch will be used as the deep learning computational framework.

Reinforcement learning is a subset of machine learning that exists alongside supervised and unsupervised learning. The goal of reinforcement learning is to develop agents (or bots) that learn to take action in such a manner as to maximize the expected cumulative reward of the selected task. For example, a bot learning to play a video game or a finance agent working to maximize the firm’s expected cumulative returns.

The agent learns through… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI