Self-Paced Deep Reinforcement Learning

04/24/2020
by   Pascal Klink, et al.
0

Generalization and reuse of agent behaviour across a variety of learning tasks promises to carry the next wave of breakthroughs in Reinforcement Learning (RL). The field of Curriculum Learning proposes strategies that aim to support a learning agent by exposing it to a tailored series of tasks throughout learning, e.g. by progressively increasing their complexity. In this paper, we consider recently established results in Curriculum Learning for episodic RL, proposing an extension that is easily integrated with well-known RL algorithms and providing a theoretical formulation from an RL-as-Inference perspective. We evaluate the proposed scheme with different Deep RL algorithms on representative tasks, demonstrating that it is capable of significantly improving learning performance.

READ FULL TEXT

Authors

page 4

page 17

page 19

10/09/2020

Learning to Locomote: Understanding How Environment Design Matters for Deep Reinforcement Learning

Learning to locomote is one of the most common tasks in physics-based an...
02/25/2021

A Probabilistic Interpretation of Self-Paced Learning with Applications to Reinforcement Learning

Across machine learning, the use of curricula has shown strong empirical...
03/14/2021

Investigating Value of Curriculum Reinforcement Learning in Autonomous Driving Under Diverse Road and Weather Conditions

Applications of reinforcement learning (RL) are popular in autonomous dr...
05/16/2022

The Primacy Bias in Deep Reinforcement Learning

This work identifies a common flaw of deep reinforcement learning (RL) a...
02/18/2020

Generating Automatic Curricula via Self-Supervised Active Domain Randomization

Goal-directed Reinforcement Learning (RL) traditionally considers an age...
10/15/2021

SaLinA: Sequential Learning of Agents

SaLinA is a simple library that makes implementing complex sequential le...
01/07/2022

Neural Network Optimization for Reinforcement Learning Tasks Using Sparse Computations

This article proposes a sparse computation-based method for optimizing n...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.