What Is Worth Representing? Representational Empowerment for Continual Model Construction
cs.LG, cs.AI
Submitted: 2026-09-02
Updated: 2026-09-02
Terminology
Sources
- Plasticity as the Mirror of Empowerment
- Exploration by Random Network Distillation
- "Just in Time" World Modeling Supports Human Planning and Reasoning
- BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning
- Diversity is All You Need: Learning Skills without a Reward Function
- Variational Intrinsic Control
- Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning
- Motif: Intrinsic Motivation from Artificial Intelligence Feedback
- Intrinsically-Motivated Humans and Agents in Open-World Exploration
- From Curiosity to Competence: How World Models Interact with the Dynamics of Exploration
- Analogy making as amortised model construction
- Foundation Policies with Hilbert Representations
- Proximal Policy Optimization Algorithms
- Learning Neuro-Symbolic Skills for Bilevel Planning
- Human-Level Reinforcement Learning through Theory-Based Modeling, Exploration, and Planning
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- Modeling Open-World Cognition as On-Demand Synthesis of Probabilistic Models
- Agent-centric learning: from external reward maximization to internal knowledge curation
- Path-dependent program induction under resource constraints explains human sequence learning
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks