Benchmark Environments for Multitask Learning in Continuous Domains

2017/08/14 by Peter Henderson, Wei-Di Chang, Henderson, Peter +9 · 2 citations
Computer Science · #Advanced Neural Network Applications #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences

paper · pdf · doi:10.48550/arxiv.1708.04352

openalex publication_date 2017/08/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

As demand drives systems to generalize to various domains and problems, the study of multitask, transfer and lifelong learning has become an increasingly important pursuit. In discrete domains, performance on the Atari game suite has emerged as the de facto benchmark for assessing multitask learning. However, in continuous domains there is a lack of agreement on standard multitask evaluation environments which makes it difficult to compare different approaches fairly. In this work, we describe a benchmark set of tasks that we have developed in an extendable framework based on OpenAI Gym. We run a simple baseline using Trust Region Policy Optimization and release the framework publicly to be expanded and used for the systematic comparison of multitask, transfer, and lifelong learning in continuous domains.

Citations

• Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning
• Benchmarking Deep Reinforcement Learning for Continuous Control
• Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic

Cited by

• Efficient Multi-Task Reinforcement Learning with Cross-Task Policy Guidance
• Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment

Related

• Task Selection Policies for Multitask Learning
• Evaluating Pretrained models for Deployable Lifelong Learning
• L2Explorer: A Lifelong Reinforcement Learning Assessment Environment
• A Continual Offline Reinforcement Learning Benchmark for Navigation Tasks
• Design Perspectives of Multitask Deep Learning Models and Applications