Cover Image

Path Channels and Plan Extension Kernels: a Mechanistic Description of Planning in a Sokoban RNN

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Taufeeque, Mohammad, Tucker, Aaron David, Gleave, Adam, Garriga-Alonso, Adrià
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Planning in a recurrent neural network that plays Sokoban
by: Taufeeque, Mohammad, et al.
Published: (2024)

The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes
by: Taufeeque, Mohammad, et al.
Published: (2026)

Interpreting Emergent Planning in Model-Free Reinforcement Learning
by: Bush, Thomas, et al.
Published: (2025)

SynthSAEBench: Evaluating Sparse Autoencoders on Scalable Realistic Synthetic Data
by: Chanin, David, et al.
Published: (2026)

Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders
by: Chanin, David, et al.
Published: (2025)

Among Us: A Sandbox for Measuring and Detecting Agentic Deception
by: Golechha, Satvik, et al.
Published: (2025)

Exploiting Novel GPT-4 APIs
by: Pelrine, Kellin, et al.
Published: (2023)

Feature Hedging: Correlated Features Break Narrow Sparse Autoencoders
by: Chanin, David, et al.
Published: (2025)

Biases in the Blind Spot: Detecting What LLMs Fail to Mention
by: Arcuschin, Iván, et al.
Published: (2026)

Preference Learning with Lie Detectors can Induce Honesty or Evasion
by: Cundy, Chris, et al.
Published: (2025)

DiFR: Inference Verification Despite Nondeterminism
by: Karvonen, Adam, et al.
Published: (2025)

Towards Bio-Inspired Robotic Trajectory Planning via Self-Supervised RNN
by: Cibula, Miroslav, et al.
Published: (2025)

Where's the Plan? Locating Latent Planning in Language Models with Lightweight Mechanistic Interventions
by: Ma, Nicole, et al.
Published: (2026)

Concept Influence: Leveraging Interpretability to Improve Performance and Efficiency in Training Data Attribution
by: Kowal, Matthew, et al.
Published: (2026)

Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels
by: Beck, Maximilian, et al.
Published: (2025)

Path Planning for Masked Diffusion Model Sampling
by: Peng, Fred Zhangzhi, et al.
Published: (2025)

Hypothesis Testing the Circuit Hypothesis in LLMs
by: Shi, Claudia, et al.
Published: (2024)

A New View on Planning in Online Reinforcement Learning
by: Roice, Kevin, et al.
Published: (2024)

Goal-Space Planning with Subgoal Models
by: Lo, Chunlok, et al.
Published: (2022)

Enhancing UAV Path Planning Efficiency Through Accelerated Learning
by: Viana, Joseanne, et al.
Published: (2025)

Exposing the Systematic Vulnerability of Open-Weight Models to Prefill Attacks
by: Struppek, Lukas, et al.
Published: (2026)

Planner-Admissible Graph-PDE Value Extensions for Sparse Goal-Conditioned Planning
by: Zhang, Shiheng
Published: (2026)

Can Go AIs be adversarially robust?
by: Tseng, Tom, et al.
Published: (2024)

Learning Social Heuristics for Human-Aware Path Planning
by: Eirale, Andrea, et al.
Published: (2025)

TA-RNN: an Attention-based Time-aware Recurrent Neural Network Architecture for Electronic Health Records
by: Olaimat, Mohammad Al, et al.
Published: (2024)

Scaling Trends for Data Poisoning in LLMs
by: Bowen, Dillon, et al.
Published: (2024)

Learn Once Plan Arbitrarily (LOPA): Attention-Enhanced Deep Reinforcement Learning Method for Global Path Planning
by: Huang, Guoming, et al.
Published: (2024)

AI Companies Should Report Pre- and Post-Mitigation Safety Evaluations
by: Bowen, Dillon, et al.
Published: (2025)

InterpBench: Semi-Synthetic Transformers for Evaluating Mechanistic Interpretability Techniques
by: Gupta, Rohan, et al.
Published: (2024)

Stabilizing RNN Gradients through Pre-training
by: Herranz-Celotti, Luca, et al.
Published: (2023)

Plantain: Plan-Answer Interleaved Reasoning
by: Liang, Anthony, et al.
Published: (2025)

STARC: A General Framework For Quantifying Differences Between Reward Functions
by: Skalse, Joar, et al.
Published: (2023)

Public Transit Arrival Prediction: a Seq2Seq RNN Approach
by: Bhutani, Nancy, et al.
Published: (2022)

Actionable Counterfactual Explanations Using Bayesian Networks and Path Planning with Applications to Environmental Quality Improvement
by: Valero-Leal, Enrique, et al.
Published: (2025)

HadamRNN: Binary and Sparse Ternary Orthogonal RNNs
by: Foucault, Armand, et al.
Published: (2025)

Reflect-then-Plan: Offline Model-Based Planning through a Doubly Bayesian Lens
by: Jeong, Jihwan, et al.
Published: (2025)

Random Network Distillation Based Deep Reinforcement Learning for AGV Path Planning
by: Yin, Huilin, et al.
Published: (2024)

Multi-Robot Path Planning Combining Heuristics and Multi-Agent Reinforcement Learning
by: Peng, Shaoming
Published: (2023)

PPNet: A Two-Stage Neural Network for End-to-end Path Planning
by: Meng, Qinglong, et al.
Published: (2024)

ARDDQN: Attention Recurrent Double Deep Q-Network for UAV Coverage Path Planning and Data Harvesting
by: Kumar, Praveen, et al.
Published: (2024)