4 papers · 1 filter
Deep SPI: Safe Policy Improvement via World Models
Florent Delgrange, Raphael Avalos, Willem Röpke
Safe policy improvement (SPI) offers theoretical control over policy updates, yet existing guarantees largely concern offline, tabular reinforcement learning (RL). We study SPI in…
Dynamic Size Message Scheduling for Multi-Agent Communication under Limited Bandwidth
Qingshuang Sun, Denis Steckelmacher, Yuan Yao +2
Communication plays a vital role in multi-agent systems, fostering collaboration and coordination. However, in real-world scenarios where communication is bandwidth-limited, existi…
The Wasserstein Believer: Learning Belief Updates for Partially Observable Environments through Reliable Latent Space Models
Raphael Avalos, Florent Delgrange, Ann Nowé +2
Partially Observable Markov Decision Processes (POMDPs) are used to model environments where the full state cannot be perceived by an agent. As such the agent needs to reason takin…
Local Advantage Networks for Cooperative Multi-Agent Reinforcement Learning
Raphaël Avalos, Mathieu Reymond, Ann Nowé +1
Many recent successful off-policy multi-agent reinforcement learning (MARL) algorithms for cooperative partially observable environments focus on finding factorized value functions…