PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning

Understand

In Reinforcement Learning (RL), enhancing sample efficiency is crucial, particularly in scenarios when data acquisition is costly and risky.

• In principle, off-policy RL algorithms can improve sample efficiency by allowing multiple updates per environment interaction.
• However, these multiple updates often lead the model to overfit to earlier interactions, which is referred to as the loss of plasticity.
• Our study investigates the underlying causes of this phenomenon by dividing plasticity into two aspects.