activity
20222026
most citedA Conservative Q-Learning approach for handling distribution shift in sepsis treatment strategies

6 citations · 6 across the 5 of their papers we have counts for

collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2026

Inducing Emergent Misalignment from Reward Hacks with Iterative DPO

Oliver Daniels, Perusha Moodley, Benjamin M. Marlin +1

Reward hacking during reinforcement learning from verifiable rewards (RLVR) can induce reward seeking and broad misalignment in language models. Studying this misgeneralization is…

cs.LG2026

Exploration Hacking: Can LLMs Learn to Resist RL Training?

Eyon Jang, Damon Falck, Joschka Braun +6

Reinforcement learning (RL) has become essential to the post-training of large language models (LLMs) for reasoning, agentic capabilities and alignment. Successful RL relies on suf…

cs.LG2026

Stress-Testing Alignment Audits With Prompt-Level Strategic Deception

Oliver Daniels, Perusha Moodley, Benjamin M. Marlin +1

Alignment audits aim to robustly identify hidden goals from strategic, situationally aware misaligned models. Despite this threat model, existing auditing methods have not been sys…

cs.LG2024

Multi-State-Action Tokenisation in Decision Transformers for Multi-Discrete Action Spaces

Perusha Moodley, Pramod Kaushik, Dhillu Thambi +4

Decision Transformers, in their vanilla form, struggle to perform on image-based environments with multi-discrete action spaces. Although enhanced Decision Transformer architecture…

cs.LG20226 cited

A Conservative Q-Learning approach for handling distribution shift in sepsis treatment strategies

Pramod Kaushik, Sneha Kummetha, Perusha Moodley +1

Sepsis is a leading cause of mortality and its treatment is very expensive. Sepsis treatment is also very challenging because there is no consensus on what interventions work best…