Building World Models from Intrinsic Motivation
cs.AI, cs.LG
Submitted: 2026-11-09
Updated: 2026-11-09
Project page: https://neuroagents-lab.github.io/ssrl-agent
Terminology
Sources
- Variational Option Discovery Algorithms
- Zero-shot World Models Are Developmentally Efficient Learners
- Never Give Up: Learning Directed Exploration Strategies
- Learning to Perceive the World Through Control: Empowerment-Based Representation Learning
- Next Embedding Prediction Makes World Models Stronger
- Exploration by Random Network Distillation
- Tactile Genesis: Exploring Tactile Sensors at Scale for Learning Dexterous Tasks
- CIG: Exploration via Conditional Information Gain
- World Modeling with Probabilistic Structure Integration
- Efficient Exploration via State Marginal Matching
- Discovering and Achieving Goals via World Models
- Temporal Representations for Exploration: Learning Complex Exploratory Behavior without Extrinsic Rewards
- Variational Information Maximisation for Intrinsically Motivated Reinforcement Learning
- RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots
- What Capable Agents Must Know: Selection Theorems for Robust Decision-Making under Uncertainty
- Proximal Policy Optimization Algorithms
- Dynamics-Aware Unsupervised Discovery of Skills
- DeepMind Control Suite
- Efficient Empowerment Estimation for Unsupervised Stabilization
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents