FlexLoop: Depth-Elastic Looped Policies for Adaptive Test-Time Computation in Deep RL
cs.LG, cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Sources
- Is Temporal Difference Learning the Gold Standard for Stitching in RL?
- Scaling Laws for Neural Language Models
- Adaptive Depth in Looped Transformers: Diagnosing Learned Halting Gates and Trajectory Readouts
- Proximal Policy Optimization Algorithms
- Depth-adaptive Inference of Looped Language Models via Continuous Depth Batching
- Scaling Latent Reasoning via Looped Language Models
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