SkillRary

Bitte logge dich ein, um einen Kommentar zu schreiben

Deep Reinforcement Learning

  • Amruta Bhaskar
  • Jun 30, 2021
  • 0 Bemerkungen)
  • 1499 Ansichten

 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.

Deep reinforcement learning combines artificial neural networks with a framework of reinforcement learning that helps software agents learn how to reach their goals. That is, it unites function approximation and target optimization, mapping state-action pairs to expected rewards.

While neural networks are responsible for recent AI breakthroughs in problems like computer vision, machine translation and time series prediction – they can also combine with reinforcement learning algorithms to create something astounding like Deepmind’s AlphaGo, an algorithm that beat the world champions of the Go board game.

Reinforcement learning refers to goal-oriented algorithms, which learn how to achieve a complex objective (goal) or how to maximize along a particular dimension over many steps; for example, they can maximize the points won in a game over many moves. RL algorithms can start from a blank slate, and under the right conditions, achieve superhuman performance. Like a pet incentivized by scolding and treats, these algorithms are penalized when they make the wrong decisions and rewarded when they make the right ones – this is reinforcement.

Reinforcement algorithms that incorporate deep neural networks can beat human experts playing numerous Atari video games, Starcraft II and Dota-2. While that may sound trivial to non-gamers, it’s a vast improvement over reinforcement learning’s previous accomplishments, and the state of the art is progressing rapidly.

Reinforcement learning solves the difficult problem of correlating immediate actions with the delayed outcomes they produce. Like humans, reinforcement learning algorithms sometimes have to wait to see the fruit of their decisions. They operate in a delayed-return environment, where it can be difficult to understand which action leads to which outcome over many time steps.

Reinforcement learning algorithms are slowly performing better and better in more ambiguous, real-life environments while choosing from an arbitrary number of possible actions, rather than from the limited options of a repeatable video game. That is, they are beginning to achieve goals in the real world. If you have measurable KPIs to reach, deep RL may be able to help.

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.

  • Manufacturing

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.

  • Automotive

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.

  • Finance

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.

  • Healthcare

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.

  • Bots

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.

Bitte logge dich ein, um einen Kommentar zu schreiben

( 0 ) Bemerkungen)