Representation over Routing: Diagnosing Temporal Routing Pathologies in Multi-Timescale PPO
Temporal credit assignment in reinforcement learning is often approached by introducing value estimates at multiple discount factors. A natural next step is to let the actor dynamically route among these temporal heads, using either differentiable attention or heuristic uncertainty weights. This paper argues that such routing can create a numerical shortcut rather than a reliable temporal abstraction. We study this issue in a controlled PPO setting on LunarLander-v2, using the environment as a v
Record details
Published: 15 April 2026
Source: arXiv
Category: Research
Topics: Healthcare · Environment
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Toward Zero-Egress Psychiatric AI: On-Device LLM Deployment for Privacy-Preserving Mental Health Decision Support
arXiv · 20 April 2026
An empirical evaluation of the risks of AI model updates using clinical data: stability, arbitrariness, and fairness
arXiv · 27 April 2026
Benchmarking the Safety of Large Language Models for Robotic Health Attendant Control
arXiv · 29 April 2026
Train the Trainers -- An Agentic AI Framework for Peer-Based Mental Health Support in Battlefield Environments
arXiv · 31 March 2026
Multi-element Persuasion in Social Media Health Communication: Synergistic and Trade-off Effects
arXiv · 30 April 2026
Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses
arXiv · 28 March 2026
How to cite this record
ethics.ai (15 April 2026), “Representation over Routing: Diagnosing Temporal Routing Pathologies in Multi-Timescale PPO,” evidence record 5844, https://ethics.ai/record/5844 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.