2 citations · 3 across the 6 of their papers we have counts for
7 papers
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.…
Leveraging weights signals -- Predicting and improving generalizability in reinforcement learning
Olivier Moulin, Vincent Francois-lavet, Paul Elbers +1
Generalizability of Reinforcement Learning (RL) agents (ability to perform on environments different from the ones they have been trained on) is a key problem as agents have the te…
Hadamax Encoding: Elevating Performance in Model-Free Atari
Jacob E. Kooi, Zhao Yang, Vincent François-Lavet
Neural network architectures have a large impact in machine learning. In reinforcement learning, network architectures have remained notably simple, as changes often lead to small…
Improving generalization in reinforcement learning through forked agents
Olivier Moulin, Vincent Francois-Lavet, Mark Hoogendoorn
An eco-system of agents each having their own policy with some, but limited, generalizability has proven to be a reliable approach to increase generalization across procedurally ge…
Disentangled (Un)Controllable Features
Jacob E. Kooi, Mark Hoogendoorn, Vincent François-Lavet
In the context of MDPs with high-dimensional states, downstream tasks are predominantly applied on a compressed, low-dimensional representation of the original input space. A varie…
A Meta-Reinforcement Learning Algorithm for Causal Discovery
Andreas Sauter, Erman Acar, Vincent François-Lavet
Causal discovery is a major task with the utmost importance for machine learning since causal structures can enable models to go beyond pure correlation-based inference and signifi…
Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey
Amjad Yousef Majid, Serge Saaybi, Tomas van Rietbergen +3
Deep Reinforcement Learning (DRL) and Evolution Strategies (ESs) have surpassed human-level control in many sequential decision-making problems, yet many open challenges still exis…