Distributional Reinforcement Learning for Efficient Exploration
원문 초록
In distributional reinforcement learning (RL), the estimated distribution of value function models both the parametric and intrinsic uncertainties. We propose a novel and efficient exploration method for deep RL that has two components. The first is a decaying schedule to suppress the intrinsic uncertainty. The second is an exploration bonus calculated from the upper quantiles of the learned distribution. In Atari 2600 games, our method outperforms QR-DQN in 12 out of 14 hard games (achieving 483 \% average gain across 49 games in cumulative rewards over QR-DQN with a big win in Venture). We also compared our algorithm with QR-DQN in a challenging 3D driving simulator (CARLA). Results show that our algorithm achieves near-optimal safety rewards twice faster than QRDQN.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
PGDQN: Preference-Guided Deep Q-Network
Multirobot Coverage of Modular Environments
Margin Trader: A Reinforcement Learning Framework for Portfolio Management with Margin and Constraints
Multi-modal Siamese Network for Entity Alignment
Task Independent Capsule-Based Agents for Deep Q-Learning
Accelerating lifelong reinforcement learning via reshaping rewards
토론
이 논문과 연결된 포럼 글이 아직 없습니다.