# Latent Skill Planning for Exploration and Transfer

arXiv: https://arxiv.org/abs/2011.13897 · HTML: https://mlsanity.com/paper/2011.13897/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Nov 2020.

## Built on by (most cited first, 19 of 19)

- [Reinforcement Learning with Action Chunking](https://mlsanity.com/paper/2507.07969/) (2025)
- [Tutorial on amortized optimization](https://mlsanity.com/paper/2202.00665/) (2022)
- [Simple Hierarchical Planning with Diffusion](https://mlsanity.com/paper/2401.02644/) (2024)
- [CACTI: A Framework for Scalable Multi-Task Multi-Scene Visual Imitation Learning](https://mlsanity.com/paper/2212.05711/) (2022)
- [Accelerating Robotic Reinforcement Learning via Parameterized Action Primitives](https://mlsanity.com/paper/2110.15360/) (2021)
- [Skill-based Model-based Reinforcement Learning](https://mlsanity.com/paper/2207.07560/) (2022)
- [Choreographer: Learning and Adapting Skills in Imagination](https://mlsanity.com/paper/2211.13350/) (2022)
- [Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective](https://mlsanity.com/paper/2209.08466/) (2022)
- [INFOrmation Prioritization through EmPOWERment in Visual Model-Based RL](https://mlsanity.com/paper/2204.08585/) (2022)
- [Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration](https://mlsanity.com/paper/2410.18076/) (2024)
- [Exploring the limits of Hierarchical World Models in Reinforcement Learning](https://mlsanity.com/paper/2406.00483/) (2024)
- [Predictable MDP Abstraction for Unsupervised Model-Based RL](https://mlsanity.com/paper/2302.03921/) (2023)
- [Compositional Planning with Jumpy World Models](https://mlsanity.com/paper/2602.19634/) (2026)
- [SAFER: Data-Efficient and Safe Reinforcement Learning via Skill Acquisition](https://mlsanity.com/paper/2202.04849/) (2022)
- [Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning](https://mlsanity.com/paper/2310.00229/) (2023)
- [Priors, Hierarchy, and Information Asymmetry for Skill Transfer in Reinforcement Learning](https://mlsanity.com/paper/2201.08115/) (2022)
- [Dream-MPC: Gradient-Based Model Predictive Control with Latent Imagination](https://mlsanity.com/paper/2605.04568/) (2026)
- [Adaptive Q-Chunking for Offline-to-Online Reinforcement Learning](https://mlsanity.com/paper/2605.05544/) (2026)
- [Learning Task Belief Similarity with Latent Dynamics for Meta-Reinforcement Learning](https://mlsanity.com/paper/2506.19785/) (2025)

## Abstract (arXiv)

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: https://sites.google.com/view/latent-skill-planning/