Factorized Spectral Representations for Reinforcement Learning
cs.LG
Submitted: 2026-07-15
Updated: 2026-10-29
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Shift Before You Learn: Enabling Low-Rank Representations in Reinforcement Learning
- Spectral Representation-based Reinforcement Learning
- Noise Contrastive Estimation and Negative Sampling for Conditional Models: Consistency and Statistical Efficiency
- Spectral Entry-wise Matrix Estimation for Low-Rank Reinforcement Learning
- DeepMind Control Suite
- Representation Learning with Contrastive Predictive Coding
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