Skip to yearly menu bar Skip to main content


Latent Skill Planning for Exploration and Transfer

Kevin Xie · Homanga Bharadhwaj · Danijar Hafner · Animesh Garg · Florian Shkurti


Keywords: [ Partial Amortization ] [ Model Predictive Control ] [ planning ] [ mutual information ] [ skill discovery ] [ World Models ] [ model-based reinforcement learning ]


To quickly solve new tasks in complex environments, intelligent agents need to build up reusable knowledge. For example, a learned world model captures knowledge about the environment that applies to new tasks. Similarly, skills capture general behaviors that can apply to new tasks. In this paper, we investigate how these two approaches can be integrated into a single reinforcement learning agent. Specifically, we leverage the idea of partial amortization for fast adaptation at test time. For this, actions are produced by a policy that is learned over time while the skills it conditions on are chosen using online planning. We demonstrate the benefits of our design decisions across a suite of challenging locomotion tasks and demonstrate improved sample efficiency in single tasks as well as in transfer from one task to another, as compared to competitive baselines. Videos are available at:

Chat is not available.