Looped Actor: Depth-Recurrent Reasoning Models for Reinforcement Learning
cs.LG
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/camail-official/LoopedActor
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Temporal Recurrence Favors Fewer Layers
- PonderNet: Learning to Ponder
- ARC Prize 2024: Technical Report
- Universal Transformers
- TQL: Scaling Q-Functions with Transformers by Preventing Attention Collapse
- TreeQN and ATreeC: Differentiable Tree-Structured Models for Deep Reinforcement Learning
- Solve the Loop: Attractor Models for Language and Reasoning
- Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation
- On the Role of Computation in Reinforcement Learning
- Adaptive Computation Time for Recurrent Neural Networks
- Training Large Language Models to Reason in a Continuous Latent Space
- Equilibrium Reasoners: Learning Attractors Enables Scalable Reasoning
- Less is More: Recursive Reasoning with Tiny Networks
- From Growing to Looping: A Unified View of Iterative Computation in LLMs
- Loop, Think, & Generalize: Implicit Reasoning in Recurrent-Depth Transformers
- Offline Reinforcement Learning with Implicit Q-Learning
- Looped World Models
- Fixed-Point Reasoners: Stable and Adaptive Deep Looped Transformers
- High-Dimensional Continuous Control Using Generalized Advantage Estimation
- Proximal Policy Optimization Algorithms
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