One of the most intriguing areas of artificial intelligence today is the concept of deep reinforcement learning, where machines can teach themselves based upon the results of their own actions. It is one of the areas of artificial intelligence that shows great promise, so let’s look at what it is and explore some real-world applications.
What is deep reinforcement learning?
Deep reinforcement learning is a category of machine learning and artificial intelligence where intelligent machines can learn from their actions similar to the way humans learn from experience. Inherent in this type of machine learning is that an agent is rewarded or penalised based on their actions. Actions that get them to the target outcome are rewarded (reinforced).
Through a series of trial and error, a machine keeps learning, making this technology ideal for dynamic environments that keep changing. Although reinforcement learning has been around for decades, it was much more recently combined with deep learning, which yielded phenomenal results. The “deep” portion of reinforcement learning refers to a multiple (deep) layers of artificial neural networks that replicate the structure of a human brain. Deep learning requires large amounts of training data and significant computing power. Over the last few years, the volumes of data have exploded while the costs for computing power have dramatically reduced, which has enabled the explosion of deep learning applications.
From gameplay to profit-making deep reinforcement learning
The possibilities of deep reinforcement learning came to the attention of many during the well-publicised defeat of a Go grandmaster by DeepMind’s AlphaGo. In addition to playing Go, deep reinforcement learning has achieved human-level prowess in other games such as chess, poker, Atari games and several other competitive video games. It’s taken the technology a bit of time to move from board games to boardrooms for a couple of reasons including:
- There needed to be products and services to support deep reinforcement learning. For example, simulation technology helps provide a trial-and-error environment for deep reinforcement learning that is scalable and where mistakes won’t cause real-world damage. Services needed to be available to offer simulation technology for multiple interacting machines.
- Subject matter experts need an easy-to-use deep reinforcement learning (DRL) interface—rather than be DRL experts—to fully leverage the technology for business problems.
Practical applications of deep reinforcement learning
AI toolkits for training
AI toolkits such as OpenAI Gym, DeepMind Lab and Psychlab are providing the training environment that was necessary to catapult large-scale innovation for deep reinforcement learning. These open-source tools train DRL agents. As more organisations apply deep reinforcement learning to their own unique business use cases, we will continue to see dramatic growth in practical applications.
Intelligent robots are becoming more commonplace in warehouse and fulfilment centres to sort out millions of products and deliver them to the right people. When a robot picks a device to put in a container, deep reinforcement learning helps it gain knowledge based on whether it succeeded or failed. It uses this knowledge to perform more efficiently in the future.
The automotive industry has a diverse and large dataset that will power deep reinforcement learning. Already in use for autonomous vehicles, it will help transform factories, vehicle maintenance and overall automation in the industry. The industry is driven by safety, quality and cost and DRL with data from customers, dealers and warranties will provide new ways to improve quality, save money and have a higher safety record.
Using artificial intelligence, including deep reinforcement learning, to be better investment managers than humans and to evaluate trading strategies is the core objective of Pit.AI.
From determining the optimal treatment plans and diagnosis to clinical trials, new drug development and automatic treatment, there is great potential for deep reinforcement learning to improve healthcare.
The conversational UI paradigm that makes AI bots possible leverages the power of deep reinforcement learning. The bots are rapidly learning the nuances and semantics of language over many domains for automated speech and natural language understanding thanks to deep reinforcement learning.
There is much excitement about the potential for deep reinforcement learning. Since this segment of artificial intelligence learns by interacting with its environment, there is really no limit to the possible applications.