Learning Actions and Control of Focus of Attention with a Log-Polar-like Sensor
원문 초록
With the long-term goal of reducing the image processing time on an autonomous mobile robot in mind we explore in this paper the use of log-polar like image data with gaze control. The gaze control is not done on the Cartesian image but on the log-polar like image data. For this we start out from the classic deep reinforcement learning approach for Atari games. We extend an A3C deep RL approach with an LSTM network, and we learn the policy for playing three Atari games and a policy for gaze control. While the Atari games already use low-resolution images of 80 by 80 pixels, we are able to further reduce the amount of image pixels by a factor of 5 without losing any gaming performance.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Generalized Adaptive Transfer Network: Enhancing Transfer Learning in Reinforcement Learning Across Domains
Adaptive Action Duration with Contextual Bandits for Deep Reinforcement Learning in Dynamic Environments
Unraveling the Rainbow: can value-based methods schedule?
Pay Attention to What and Where? Interpretable Feature Extractor in Vision-based Deep Reinforcement Learning
Automatic Reward Shaping from Confounded Offline Data
Adventurer: Exploration with BiGAN for Deep Reinforcement Learning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.