Training Agents using Upside-Down Reinforcement Learning

12/05/2019
by   Rupesh Kumar Srivastava, et al.
15

Traditional Reinforcement Learning (RL) algorithms either predict rewards with value functions or maximize them using policy search. We study an alternative: Upside-Down Reinforcement Learning (Upside-Down RL or UDRL), that solves RL problems primarily using supervised learning techniques. Many of its main principles are outlined in a companion report [34]. Here we present the first concrete implementation of UDRL and demonstrate its feasibility on certain episodic learning problems. Experimental results show that its performance can be surprisingly competitive with, and even exceed that of traditional baseline algorithms developed over decades of research.

READ FULL TEXT
research
04/10/2018

Gotta Learn Fast: A New Benchmark for Generalization in RL

In this report, we present a new reinforcement learning (RL) benchmark b...
research
12/05/2019

Reinforcement Learning Upside Down: Don't Predict Rewards – Just Map Them to Actions

We transform reinforcement learning (RL) into a form of supervised learn...
research
10/25/2020

How to Make Deep RL Work in Practice

In recent years, challenging control problems became solvable with deep ...
research
02/26/2021

Low-Precision Reinforcement Learning

Low-precision training has become a popular approach to reduce computati...
research
10/16/2014

Domain-Independent Optimistic Initialization for Reinforcement Learning

In Reinforcement Learning (RL), it is common to use optimistic initializ...
research
05/13/2022

Upside-Down Reinforcement Learning Can Diverge in Stochastic Environments With Episodic Resets

Upside-Down Reinforcement Learning (UDRL) is an approach for solving RL ...
research
05/21/2018

Hierarchical Reinforcement Learning with Hindsight

Reinforcement Learning (RL) algorithms can suffer from poor sample effic...

Please sign up or login with your details

Forgot password? Click here to reset