10 citations · 20 across the 4 of their papers we have counts for
5 papers · 1 filter
F-TIS: Harnessing Diverse Models in Collaborative GRPO
Nikolay Blagoev, Oğuzhan Ersoy, Wendelin Boehmer +1
Reinforcement learning methods such as GRPO have seen great popularity in LLM post-training. In GRPO, models produce completions to a set of prompts, which are rewarded, and the po…
Value Improved Actor Critic Algorithms
Yaniv Oren, Moritz A. Zanger, Pascal R. van der Vaart +3
To learn approximately optimal acting policies for decision problems, modern Actor Critic algorithms rely on deep Neural Networks (DNNs) to parameterize the acting policy and greed…
My Body is a Cage: the Role of Morphology in Graph-Based Incompatible Control
Vitaly Kurin, Maximilian Igl, Tim Rocktäschel +2
Multitask Reinforcement Learning is a promising way to obtain models with better performance, generalisation, data efficiency, and robustness. Most existing work is limited to comp…
Transient Non-Stationarity and Generalisation in Deep Reinforcement Learning
Maximilian Igl, Gregory Farquhar, Jelena Luketina +2
Non-stationarity can arise in Reinforcement Learning (RL) even in stationary environments. For example, most RL algorithms collect new data throughout training, using a non-station…
Privileged Information Dropout in Reinforcement Learning
Pierre-Alexandre Kamienny, Kai Arulkumaran, Feryal Behbahani +2
Using privileged information during training can improve the sample efficiency and performance of machine learning systems. This paradigm has been applied to reinforcement learning…