Conservative World Models

Published: 28 Oct 2023, Last Modified: 04 Dec 2023GenPlan'23EveryoneRevisionsBibTeX
Abstract: Zero-shot reinforcement learning (RL) promises to provide agents that can perform _any_ task in an environment after an offline pre-training phase. _Forward-backward_ (FB) representations represent remarkable progress towards this ideal, achieving 85% of the performance of task-specific agents in this setting. However, such performance is contingent on access to large and diverse datasets for pre-training, which cannot be expected for most real problems. Here, we explore how FB performance degrades when trained on small datasets that lack diversity, and mitigate it with _conservatism_, a well-established feature of performant offline RL algorithms. We evaluate our family of methods across various datasets, domains and tasks, reaching 150% of vanilla FB performance in aggregate. Somewhat surprisingly, conservative FB algorithms also outperform the task-specific baseline, despite lacking access to reward labels and being required to maintain policies for all tasks. Conservative FB algorithms perform no worse than FB on full datasets, and so present little downside over their predecessor. Our code is available open-source via:
Submission Number: 12