2 papers
cs.LG2026
Hadamard Representation: Scaffolding Performance Across Model-free RL
Jacob E. Kooi, Zhao Yang, Mark Hoogendoorn +1
Deep reinforcement learning agents progressively lose representational capacity during training: neurons become dormant, removing active capacity from the network, and effective ra…
cs.LG2025
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…