Главная
Study mode:
on
1
Intro
2
Who am I
3
Who are we
4
Overview
5
Riot Games
6
Dow Chemicals
7
Recommendation systems
8
Challenges
9
The most basic challenge
10
Constraints
11
Evaluation
12
Deployment
13
Problem formulation
14
Utilities
15
Sidebyside code
16
Running evaluations
17
Serving RL models
18
Ideas are easy
19
Questions
Description:
Learn about production reinforcement learning (RL) and decision-making using RLlib in this 29-minute conference talk from Anyscale's Ray Summit 2022. Explore real-world applications of RL in industries such as gaming and chemicals, and discover how to implement recommendation systems. Address common challenges in RL, including problem formulation, constraints, evaluation, and deployment. Gain insights into utilities, side-by-side code comparisons, and techniques for running evaluations and serving RL models. Understand the complexities of implementing RL solutions in production environments and get answers to your questions about practical RL applications.

Production RL and Decision-Making with RLlib

Anyscale
Add to list
0:00 / 0:00