What Is Reinforcement Learning
Reinforcement learning is a type of machine learning that learns from its own reward and feedback, so it is also called reward-based learning. Its algorithm, inside Reinforcement Learning, keeps on training itself according to the right and wrong rewards.
We can also say that Reinforcement Learning is such a learning method that it learns from itself by giving feedback to itself. Just as a small child learns by seeing something new, in the same way Reinforcement Learning also works.
Reinforcement learning gives such an ability to any machine and software so that it can understand any situation and take a right decision on it.
There is a simple reward system inside Reinforcement Learning which gives positive and negative rewards to the algorithm (which we also call agent) according to its performance, from which the algorithm or agent keeps on learning.
Reinforcement learning also implements dynamic programming. Because here the algorithm does not have to be coded again and again after being programmed once.
Some Real World Example of Reinforcement Learning :
1. Self Driving Cars
2. advertising system of Google
3. In Robotics
4. In Deep Learning
5. In Traffic Light Control
There are many other places in which we use Reinforcement Learning.
The brittleness of deep reinforcement learning
The key advantage of reinforcement learning is its ability to develop behavior by taking actions and getting feedback, similar to the way humans and animals learn by interacting with their environment. Some scientists describe reinforcement learning as “the first computational theory of intelligence.”
The combination of reinforcement learning and deep neural networks, known as deep reinforcement learning, has been at the heart of many advances in AI, including DeepMind’s famous AlphaGo and AlphaStar models. In both cases, the AI systems were able to outmatch human world champions at their respective games.
But reinforcement learning systems are also notoriously renowned for their lack of flexibility. For example, a reinforcement learning model that can play StarCraft 2 at an expert level won’t be able to play a game with similar mechanics (e.g., Warcraft 3) at any level of competency. Even slight changes to the original game will considerably degrade the AI model’s performance.
Deep reinforcement learning
DeepMind uses deep reinforcement learning and a few clever tricks to create AI agents that can thrive in the XLand environment.
The reinforcement learning model of each agent receives a first-person view of the world, the agent’s physical state (e.g., whether it holding an object), and its current goal. Each agent finetunes the parameters of its policy neural network to maximize its rewards on the current task. The neural network architecture contains an attention mechanism to ensure the agent can balance optimization for the subgoals required to accomplish the main goal.
Once the agent masters its current challenge, the computational task generator creates a new challenge for the agent. Each new task is generated according to the agent’s training history and in a way to help distribute the agent’s skills across a vast range of challenges.
DeepMind also used its vast computational resources (courtesy of its owner Alphabet Inc.) to train a large population of agents in parallel and transfer learned parameters across different agents to improve the general capabilities of the reinforcement learning systems.
Theories of intelligence
Some of DeepMind’s top scientists published a paper recently in which they hypothesize that a single reward and reinforcement learning are enough to eventually reach artificial general intelligence (AGI). An intelligent agent with the right incentives can develop all kinds of capabilities such as perception and natural language understanding, the scientists believe.
Although DeepMind’s new approach still requires the training of reinforcement learning agents on multiple engineered rewards, it is in line with their general perspective of achieving AGI through reinforcement learning.
The gap between simulation and the real world
In a nutshell, the paper proves that if you can create a complex enough environment, design the right reinforcement learning architecture, and expose your models to enough experience (and have a lot of money to spend on compute resources), you’ll be able to generalize to various kinds of tasks in the same environment. And this is basically how natural evolution has delivered human and animal intelligence.
In fact, DeepMind has already done something similar with AlphaZero, a reinforcement learning model that managed to master multiple two-player turn-based games. The XLand experiment has extended the same notion to a much greater level by adding the zero-shot learning element.
Comments
Post a Comment