Ask a Question

Prefer a chat interface with context about you and your work?

Addressing Action Oscillations through Learning Policy Inertia

Addressing Action Oscillations through Learning Policy Inertia

Deep reinforcement learning (DRL) algorithms have been demonstrated to be effective in a wide range of challenging decision making and control tasks. However, these methods typically suffer from severe action oscillations in particular in discrete action setting, which means that agents select different actions within consecutive steps even though states …