Predictive PER: Balancing Priority and Diversity towards Stable Deep Reinforcement Learning
원문 초록
Prioritized experience replay (PER) samples important transitions, rather than uniformly, to improve the performance of a deep reinforcement learning agent. We claim that such prioritization has to be balanced with sample diversity for making the DQN stabilized and preventing forgetting. Our proposed improvement over PER, called Predictive PER (PPER), takes three countermeasures (TDInit, TDClip, TDPred) to (i) eliminate priority outliers and explosions and (ii) improve the sample diversity and distributions, weighted by priorities, both leading to stabilizing the DQN. The most notable among the three is the introduction of the second DNN called TDPred to generalize the in-distribution priorities. Ablation study and full experiments with Atari games show that each countermeasure by its own way and PPER contribute to successfully enhancing stability and thus performance over PER.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Margin Trader: A Reinforcement Learning Framework for Portfolio Management with Margin and Constraints
Energy Harvesting Reconfigurable Intelligent Surface for UAV Based on Robust Deep Reinforcement Learning
Multi-modal Siamese Network for Entity Alignment
Task Independent Capsule-Based Agents for Deep Q-Learning
User Allocation in Mobile Edge Computing: A Deep Reinforcement Learning Approach
Context-aware taxi dispatching at city-scale using deep reinforcement learning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.