# Latent-Predictive Empowerment: Measuring Empowerment without a Simulator

arXiv: https://arxiv.org/abs/2410.11155 · HTML: https://mlsanity.com/paper/2410.11155/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 51 references that are in the map.
- First posted on arXiv 15 Oct 2024.

## Builds on (most cited first, 30 of 36)

- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [Diversity is All You Need: Learning Skills without a Reward Function](https://mlsanity.com/paper/1802.06070/) (2018)
- [Revisiting Feature Prediction for Learning Visual Representations from Video](https://mlsanity.com/paper/2404.08471/) (2024)
- [Dynamics-Aware Unsupervised Discovery of Skills](https://mlsanity.com/paper/1907.01657/) (2019)
- [Variational Intrinsic Control](https://mlsanity.com/paper/1611.07507/) (2016)
- [Automatic Goal Generation for Reinforcement Learning Agents](https://mlsanity.com/paper/1705.06366/) (2017)
- [Visual Reinforcement Learning with Imagined Goals](https://mlsanity.com/paper/1807.04742/) (2018)
- [Go-Explore: a New Approach for Hard-Exploration Problems](https://mlsanity.com/paper/1901.10995/) (2019)
- [Efficient Exploration via State Marginal Matching](https://mlsanity.com/paper/1906.05274/) (2019)
- [Skew-Fit: State-Covering Self-Supervised Reinforcement Learning](https://mlsanity.com/paper/1903.03698/) (2019)
- [Variational Information Maximisation for Intrinsically Motivated Reinforcement Learning](https://mlsanity.com/paper/1509.08731/) (2015)
- [Fast Task Inference with Variational Intrinsic Successor Features](https://mlsanity.com/paper/1906.05030/) (2019)
- [Discovering and Achieving Goals via World Models](https://mlsanity.com/paper/2110.09514/) (2021)
- [Variational Option Discovery Algorithms](https://mlsanity.com/paper/1807.10299/) (2018)
- [Explore, Discover and Learn: Unsupervised Discovery of State-Covering Skills](https://mlsanity.com/paper/2002.03647/) (2020)
- [Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learning](https://mlsanity.com/paper/2007.02832/) (2020)
- [METRA: Scalable Unsupervised RL with Metric-Aware Abstraction](https://mlsanity.com/paper/2310.08887/) (2023)
- [BYOL-Explore: Exploration by Bootstrapped Prediction](https://mlsanity.com/paper/2206.08332/) (2022)
- [Empowerment -- an Introduction](https://mlsanity.com/paper/1310.1863/) (2013)
- [Shaping Belief States with Generative Environment Models for RL](https://mlsanity.com/paper/1906.09237/) (2019)
- [Lipschitz-constrained Unsupervised Skill Discovery](https://mlsanity.com/paper/2202.00914/) (2022)
- [Controllability-Aware Unsupervised Skill Discovery](https://mlsanity.com/paper/2302.05103/) (2023)
- [Hierarchical Reinforcement Learning with Advantage-Based Auxiliary Rewards](https://mlsanity.com/paper/1910.04450/) (2019)
- [Learning more skills through optimistic exploration](https://mlsanity.com/paper/2107.14226/) (2021)
- [Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective](https://mlsanity.com/paper/2209.08466/) (2022)
- [AvE: Assistance via Empowerment](https://mlsanity.com/paper/2006.14796/) (2020)

## Built on by (most cited first, 1 of 1)

- [Temporal Representations for Exploration: Learning Complex Exploratory Behavior without Extrinsic Rewards](https://mlsanity.com/paper/2603.02008/) (2026)

## Abstract (arXiv)

Empowerment has the potential to help agents learn large skillsets, but is not yet a scalable solution for training general-purpose agents. Recent empowerment methods learn diverse skillsets by maximizing the mutual information between skills and states; however, these approaches require a model of the transition dynamics, which can be challenging to learn in realistic settings with high-dimensional and stochastic observations. We present Latent-Predictive Empowerment (LPE), an algorithm that can compute empowerment in a more practical manner. LPE learns large skillsets by maximizing an objective that is a principled replacement for the mutual information between skills and states and that only requires a simpler latent-predictive model rather than a full simulator of the environment. We show empirically in a variety of settings--including ones with high-dimensional observations and highly stochastic transition dynamics--that our empowerment objective (i) learns similar-sized skillsets as the leading empowerment algorithm that assumes access to a model of the transition dynamics and (ii) outperforms other model-based approaches to empowerment.