Can I read Mitigating Plasticity Loss in On-Policy RL on EtoBox?

Mitigating Plasticity Loss in On-Policy RL by devilevilsn is a document available to read on EtoBox.

What is Mitigating Plasticity Loss in On-Policy RL about?

This study investigates plasticity loss in on-policy deep reinforcement learning (RL), where neural networks struggle to adapt to new tasks over time. The authors conduct experiments to show that traditional mitigation methods from supervised and off-policy learning often fail in this context, while

Author

devilevilsn

Language

EN