Benchmark Environments for Multitask Learning in Continuous Domains
This work provides a standardized evaluation environment for researchers in multitask, transfer, and lifelong learning in continuous domains, which is incremental as it builds on existing tools like OpenAI Gym.
The authors addressed the lack of standard benchmarks for multitask learning in continuous domains by developing an extendable framework based on OpenAI Gym, and they released it publicly with a baseline using Trust Region Policy Optimization for systematic comparison.
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.