Does Learning Recurrent Networks Matter in Partially Observable RL?
cs.LG, cs.AI
Submitted: 2026-10-09
Updated: 2026-10-09
Code: https://github.com/Aphlios/FRN-POMDP
Project page: https://ctallec.github.io/world-models
Sources
- Layer Normalization
- On the stability properties of Gated Recurrent Units neural networks
- Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models
- Deep Transformer Q-Networks for Partially Observable Reinforcement Learning
- Gemma 3 Technical Report
- Reservoir Computing Generalized
- Reservoir Computing for Fast, Simplified Reinforcement Learning on Memory Tasks
- Proximal Policy Optimization Algorithms
- LLaMA: Open and Efficient Foundation Language Models
- Unsupervised Predictive Memory in a Goal-Directed Agent
- Qwen3 Technical Report
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: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks