How rewards teach reinforcement learning agents to behave - Deepstash
How rewards teach reinforcement learning agents to behave

How rewards teach reinforcement learning agents to behave

Curated from: thenextweb.com

Ideas, facts & insights covering these topics:

4 ideas

·

153 reads

4

Explore the World's Best Ideas

Join today and uncover 100+ curated journeys from 50+ topics. Unlock access to our mobile app with extensive features.

Reinforcement Learning

Reinforcement Learning

In reinforcement learning (RL), a software agent learns through trial and error. When it takes the desired action, the model receives a reward.

Over time, the agent works out how to execute the task to optimize its reward.

The technique can be applied to a vast array of tasks, from controlling autonomous vehicles to improving energy efficiency. But its most celebrated achievements have come in the world of games.

10

81 reads

The AlphaGo Milestone

The AlphaGo Milestone

In March 2016, the Reinforcement Learning technique had a landmark moment. 

A DeepMind system called AlphaGo became the first computer program to defeat a world champion in Go, a famously complex board game.

The victory was reportedly watched by over 200 million people.

AlphaGo learns the game from scratch by playing against different versions of itself thousands of times, incrementally learning through a process of trial and error, known as reinforcement learning. This means it is free to learn the game for itself, unconstrained by orthodox thinking.

12

23 reads

How a Reward Function Works

How a Reward Function Works

In AI systems, the rewards and punishments are calculated mathematically. A self-driving system could receive a -1 when the model hits a wall, and a +1 if it safely passes another car. These signals allow the agent to evaluate its performance.

The algorithm then learns through trial and error to maximize the reward — and ultimately, complete the task in the most desirable manner.

10

24 reads

The Bottom Line

The Bottom Line

There are still major challenges to overcome. RL agents struggle to maximize rewards in complex environments and assess the long-term repercussions of their actions. Nonetheless, the reward-is-enough proponents believe the algorithms’ adaptability could pave a path to AGI.

10

25 reads

IDEAS CURATED BY

theodorexh

There is a difference between patience & procrastination.

Theodore H.'s ideas are part of this journey:

Machine Learning With Google

Learn more about artificialintelligence with this collection

Understanding machine learning models

Improving data analysis and decision-making

How Google uses logic in machine learning

Related collections

Read & Learn

20x Faster

without
deepstash

with
deepstash

with

deepstash

Personalized microlearning

100+ Learning Journeys

Access to 200,000+ ideas

Access to the mobile app

Unlimited idea saving

Unlimited history

Unlimited listening to ideas

Downloading & offline access

Supercharge your mind with one idea per day

Enter your email and spend 1 minute every day to learn something new.

Email

I agree to receive email updates