arXiv:2506.21367
rQdia: Regularizing Q-Value Distributions With Image Augmentation
원문 초록
rQdia regularizes Q-value distributions with augmented images in pixel-based deep reinforcement learning. With a simple auxiliary loss, that equalizes these distributions via MSE, rQdia boosts DrQ and SAC on 9/12 and 10/12 tasks respectively in the MuJoCo Continuous Control Suite from pixels, and Data-Efficient Rainbow on 18/26 Atari Arcade environments. Gains are measured in both sample efficiency and longer-term training. Moreover, the addition of rQdia finally propels model-free continuous control from pixels over the state encoding baseline.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
DR-SAC: Distributionally Robust Soft Actor-Critic for Reinforcement Learning under Uncertainty
Wasserstein Barycenter Soft Actor-Critic
Cache-Efficient Posterior Sampling for Reinforcement Learning with LLM-Derived Priors Across Discrete and Continuous Domains
Offline Multi-agent Reinforcement Learning via Score Decomposition
A novel DDPG method with prioritized experience replay
Deep Reinforcement Learning with Gradient Eligibility Traces
토론
이 논문과 연결된 포럼 글이 아직 없습니다.