We methodologically address the problem of Q-value overestimation in deep reinforcement learning to handle high-dimensional state spaces efficiently. By adapting concepts from information theory, we introduce an intrinsic penalty signal encouraging reduced Q-value estimates... (read more)
PDFMETHOD | TYPE | |
---|---|---|
🤖 No Methods Found | Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet |