Probabilistic World Modeling with Asymmetric Distance Measure
On the map: World models → Latent predictive world models
Abstract (arXiv)
Representation learning is a fundamental task in machine learning, aiming at uncovering structures from data to facilitate subsequent tasks. However, what is a good representation for planning and reasoning in a stochastic world remains an open problem. In this work, we posit that learning a distance function is essential to allow planning and reasoning in the representation space. We show that a geometric abstraction of the probabilistic world dynamics can be embedded into the representation space through asymmetric contrastive learning. Unlike previous approaches that focus on learning mutual similarity or compatibility measures, we instead learn an asymmetric similarity function that reflects the state reachability and allows multi-way probabilistic inference. Moreover, by conditioning on a common reference state (e.g. the observer's current state), the learned representation space allows us to discover the geometrically salient states that only a handful of paths can lead through. These states can naturally serve as subgoals to break down long-horizon planning tasks. We evaluate our method in gridworld environments with various layouts and demonstrate its effectiveness in discovering the subgoals.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Latent predictive world models, one of 11 directions in World models. Builds on 20 of its 26 references that are in the map. First posted on arXiv 16 Mar 2024.
Builds on
20 of 26 references.
References · 20
- 2017Attention Is All You Needcited by 59,932
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
- 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
- 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
- 2022Generative Adversarial Networkscited by 5,603
- 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
- 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
- 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
- 2020CURL: Contrastive Unsupervised Representations for Reinforcement Learningcited by 745
- 2018Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Networkcited by 415
- 2019Search on the Replay Buffer: Bridging Planning and Reinforcement Learningcited by 188
8 more
- 2018Noise Contrastive Estimation and Negative Sampling for Conditional Models: Consistency and Statistical Efficiencycited by 103
- 2024Video as the New Language for Real-World Decision Makingcited by 86
- 2018The Laplacian in RL: Learning Representations with Efficient Approximationscited by 83
- 2019InfoBot: Transfer and Exploration via the Information Bottleneckcited by 78
- 2022How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via f-Advantage Regressioncited by 65
- 2018Learning Actionable Representations with Goal-Conditioned Policiescited by 53
- 2021C-Planning: An Automatic Curriculum for Learning Goal-Reaching Taskscited by 15
- 2022Bag of Image Patch Embedding Behind the Success of Self-Supervised Learningcited by 9
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Learning Commute-Time-Preserving World Models for Planning
- 2025Cloning Deterministic Worlds: The Critical Role of Latent Geometry in Long-Horizon World Models
- 2026GeoWorld: Geometric World Models
- 2026Representation World Model: Learning States, Transition and Executable Plans in Representation
- 2026Contrastive World Models
- 2020World Model as a Graph: Learning Latent Landmarks for Planning
- 2026ATLAS: Aligned Transport of Latent Structure for Reliable World Model Planning
- 2026SCALE: State-Calibrated Latent Embeddings for JEPA Planning in the Right Geometry