# medR: Reward Engineering for Clinical Offline Reinforcement Learning via Tri-Drive Potential Functions

arXiv: https://arxiv.org/abs/2602.03305 · HTML: https://mlsanity.com/paper/2602.03305/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Safe offline RL, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 32 of its 86 references that are in the map.
- First posted on arXiv 3 Feb 2026.

## Placed in

- Offline RL and imitation learning from data / [Safe offline RL](https://mlsanity.com/offlinerl/safe-offline-rl/)

## Builds on (most cited first, 30 of 32)

- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [Offline Reinforcement Learning with Implicit Q-Learning](https://mlsanity.com/paper/2110.06169/) (2021)
- [Off-Policy Deep Reinforcement Learning without Exploration](https://mlsanity.com/paper/1812.02900/) (2018)
- [Eureka: Human-Level Reward Design via Coding Large Language Models](https://mlsanity.com/paper/2310.12931/) (2023)
- [Reward Design with Language Models](https://mlsanity.com/paper/2303.00001/) (2023)
- [Text2Reward: Reward Shaping with Language Models for Reinforcement Learning](https://mlsanity.com/paper/2309.11489/) (2023)
- [Reward (Mis)design for Autonomous Driving](https://mlsanity.com/paper/2104.13906/) (2021)
- [Reward Shaping to Mitigate Reward Hacking in RLHF](https://mlsanity.com/paper/2502.18770/) (2025)
- [On Designing Effective RL Reward at Training Time for LLM Reasoning](https://mlsanity.com/paper/2410.15115/) (2024)
- [SPA-RL: Reinforcing LLM Agents via Stepwise Progress Attribution](https://mlsanity.com/paper/2505.20732/) (2025)
- [Continuous State-Space Models for Optimal Sepsis Treatment - a Deep Reinforcement Learning Approach](https://mlsanity.com/paper/1705.08422/) (2017)
- [The Ethics of ChatGPT in Medicine and Healthcare: A Systematic Review on Large Language Models (LLMs)](https://mlsanity.com/paper/2403.14473/) (2024)
- [Improving Sepsis Treatment Strategies by Combining Deep and Kernel-Based Reinforcement Learning](https://mlsanity.com/paper/1901.04670/) (2019)
- [Transformers Can Learn Temporal Difference Methods for In-Context Reinforcement Learning](https://mlsanity.com/paper/2405.13861/) (2024)
- [Latent Reward: LLM-Empowered Credit Assignment in Episodic Reinforcement Learning](https://mlsanity.com/paper/2412.11120/) (2024)
- [Model-Based Reinforcement Learning for Sepsis Treatment](https://mlsanity.com/paper/1811.09602/) (2018)
- [Reinforcement Learning in the Era of LLMs: What is Essential? What is needed? An RL Perspective on RLHF, Prompting, and Beyond](https://mlsanity.com/paper/2310.06147/) (2023)
- [The Lighthouse of Language: Enhancing LLM Agents via Critique-Guided Improvement](https://mlsanity.com/paper/2503.16024/) (2025)
- [An Improved Multi-Output Gaussian Process RNN with Real-Time Validation for Early Sepsis Detection](https://mlsanity.com/paper/1708.05894/) (2017)
- [The RL/LLM Taxonomy Tree: Reviewing Synergies Between Reinforcement Learning and Large Language Models](https://mlsanity.com/paper/2402.01874/) (2024)
- [How Can LLM Guide RL? A Value-Based Approach](https://mlsanity.com/paper/2402.16181/) (2024)
- [Potential-Based Reward Shaping For Intrinsic Motivation](https://mlsanity.com/paper/2402.07411/) (2024)
- [Extracting Heuristics from Large Language Models for Reward Shaping in Reinforcement Learning](https://mlsanity.com/paper/2405.15194/) (2024)
- [G-Transformer: Counterfactual Outcome Prediction under Dynamic and Time-varying Treatment Regimes](https://mlsanity.com/paper/2406.05504/) (2024)
- [Assessing the Zero-Shot Capabilities of LLMs for Action Evaluation in RL](https://mlsanity.com/paper/2409.12798/) (2024)
- [QLLM: Do We Really Need a Mixing Network for Credit Assignment in Multi-Agent Reinforcement Learning?](https://mlsanity.com/paper/2504.12961/) (2025)
- [Reward Guidance for Reinforcement Learning Tasks Based on Large Language Models: The LMGT Framework](https://mlsanity.com/paper/2409.04744/) (2024)
- [UGAE: A Novel Approach to Non-exponential Discounting](https://mlsanity.com/paper/2302.05740/) (2023)
- [From Reward Shaping to Q-Shaping: Achieving Unbiased Learning with LLM-Guided Knowledge](https://mlsanity.com/paper/2410.01458/) (2024)
- [Zero-Shot LLMs in Human-in-the-Loop RL: Replacing Human Feedback for Reward Shaping](https://mlsanity.com/paper/2503.22723/) (2025)

## Abstract (arXiv)

Reinforcement Learning (RL) offers a powerful framework for optimizing dynamic treatment regimes (DTRs). However, clinical RL is fundamentally bottlenecked by reward engineering: the challenge of defining signals that safely and effectively guide policy learning in complex, sparse offline environments. Existing approaches often rely on manual heuristics that fail to generalize across diverse pathologies. To address this, we propose an automated pipeline leveraging Large Language Models (LLMs) for offline reward design and verification. We formulate the reward function using potential functions consisted of three core components: survival, confidence, and competence. We further introduce quantitative metrics to rigorously evaluate and select the optimal reward structure prior to deployment. By integrating LLM-driven domain knowledge, our framework automates the design of reward functions for specific diseases while significantly enhancing the performance of the resulting policies.