Learning POMDP World Models from Observations with Language-Model Priors
cs.LG
Submitted: 2026-05-13
Updated: 2026-11-04
Code: https://github.com/atomresearch/pinductor
Terminology
Sources
- World Models
- Training Agents Inside of Scalable World Models
- PIANIST: Learning Partially Observable World Models with LLMs for Multi-Agent Decision Making
- Tru-POMDP: Task Planning Under Uncertainty via Tree of Hypotheses and Open-Ended POMDPs
- CASSANDRA: Programmatic and Probabilistic Learning and Inference for Stochastic World Modeling
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- Variational Inference for Data-Efficient Model Learning in POMDPs
- Human-Level Reinforcement Learning through Theory-Based Modeling, Exploration, and Planning
- Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis