Deep Reinforcement Learning (DRL)

From
Jump to: navigation, search

Youtube search... ...Google search

OTHER: Policy Gradient Methods

_______________________________________________________________________________________


375px-Reinforcement_learning_diagram.svg.png 1*BEby_oK1mU8Wq0HABOqeVQ.png

Goal-oriented algorithms, which learn how to attain a complex objective (goal) or maximize along a particular dimension over many steps; for example, maximize the points won in a game over many moves. Reinforcement learning solves the difficult problem of correlating immediate actions with the delayed returns they produce. Like humans, reinforcement learning algorithms sometimes have to wait a while 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.

Importance Weighted Actor-Learner Architecture (IMPALA)

YouTube search... ...Google search

uses resources more efficiently in single-machine training but also scales to thousands of machines without sacrificing data efficiency or resource utilisation. We achieve stable learning at high throughput by combining decoupled acting and learning with a novel off-policy correction method called V-trace. IMPALA is able to achieve better performance than previous agents with less data, and crucially exhibits positive transfer between tasks as a result of its multi-task approach.

5-Figure3-1.png



DMLab-30

Youtube search... ...Google search

DMLab-30 is a collection of new levels designed using our open source RL environment DeepMind Lab. These environments enable any DeepRL researcher to test systems on a large spectrum of interesting tasks either individually or in a multi-task setting.

4d62b60c-4dcd-4774-9c75-417eba1cbbc1.png