Log In Sign Up

Self-Paced Contextual Reinforcement Learning

by   Pascal Klink, et al.

Generalization and adaptation of learned skills to novel situations is a core requirement for intelligent autonomous robots. Although contextual reinforcement learning provides a principled framework for learning and generalization of behaviors across related tasks, it generally relies on uninformed sampling of environments from an unknown, uncontrolled context distribution, thus missing the benefits of structured, sequential learning. We introduce a novel relative entropy reinforcement learning algorithm that gives the agent the freedom to control the intermediate task distribution, allowing for its gradual progression towards the target context distribution. Empirical evaluation shows that the proposed curriculum learning scheme drastically improves sample efficiency and enables learning in scenarios with both broad and sharp target context distributions in which classical approaches perform sub-optimally.


page 7

page 8


Curriculum Learning with a Progression Function

Curriculum Learning for Reinforcement Learning is an increasingly popula...

Contextualize Me – The Case for Context in Reinforcement Learning

While Reinforcement Learning (RL) has made great strides towards solving...

CLUTR: Curriculum Learning via Unsupervised Task Representation Learning

Reinforcement Learning (RL) algorithms are often known for sample ineffi...

Backward Curriculum Reinforcement Learning

The current reinforcement learning algorithm uses forward-generated traj...

DisCo RL: Distribution-Conditioned Reinforcement Learning for General-Purpose Policies

Can we use reinforcement learning to learn general-purpose policies that...

Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptation

Curriculum Reinforcement Learning (CRL) aims to create a sequence of tas...

Feature Reinforcement Learning In Practice

Following a recent surge in using history-based methods for resolving pe...