9 papers · 1 filter
Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning
Zhao Yang, Yuxuan Jiang, Ting-Chih Chen +18
Reinforcement learning (RL) has become central to LLM post-training, yet the methods that dominate current pipelines, PPO and GRPO, represent only a narrow slice of what RL offers.…
ACTIVA: Amortized Causal Effect Estimation via Transformer-based Variational Autoencoder
Andreas Sauter, Saber Salehkaleybar, Frank van Harmelen +2
Predicting post-intervention distributions from observational data is central to many scientific and decision-making problems, but remains challenging due to causal ambiguity, rest…
Every Component is a Lookup: Token Attribution and Composition from a Single Decomposition
Po-Kai Chen, Niki van Stein, Aske Plaat
Mechanistic interpretability of transformers requires identifying not just which components matter but how they compose into the computational route that produced a prediction. Bot…
Towards a Practical Understanding of Lagrangian Methods in Safe Reinforcement Learning
Lindsay Spoor, Ãlvaro Serra-Gómez, Aske Plaat +1
Safe reinforcement learning addresses constrained optimization problems where maximizing performance must be balanced against safety constraints, and Lagrangian methods are a widel…
A Unified Framework for Zero-Shot Reinforcement Learning
Jacopo Di Ventura, Jan Felix Kleuker, Aske Plaat +1
Zero-shot reinforcement learning (RL) has emerged as a setting for developing general agents, capable of solving downstream tasks without additional training or planning at test-ti…
On the Effect of Regularization in Policy Mirror Descent
Jan Felix Kleuker, Aske Plaat, Thomas Moerland
Policy Mirror Descent (PMD) has emerged as a unifying framework in reinforcement learning (RL) by linking policy gradient methods with a first-order optimization method known as mi…