반응형 RIAL2 [RIAL & DIAL] Learning to Communicate with Deep Multi-Agent Reinforcement Learning University of Oxford, United Kingdom Canadian Institute, Google DeepMind, May 2016 Abstract : MDRL에서는 효용을 극대화하기 위해, env를 감지하고 행동하는 multiple agents의 문제를 고려해야만 하므로 정보 공유를 위한 communication protocol이 필요하다. 복잡한 multi-agent env에서의 patial observability를 DNN을 수용하여 end-to-end agent 간의 학습을 해결한다. 해당 논문에서는 DQN 학습을 사용하는 RIAL(Reinforced Inter-Agent Learning)과 학습 도중 별도의 communication channel을 통해 backpropagatio.. 2022. 7. 26. RIAL & DIAL (learning communication, VB) Main Paper https://arxiv.org/pdf/1605.06676.pdf Learning to Communicate with Deep Multi-Agent Reinforcement Learning Abstract 더보기 We consider the problem of multiple agents sensing and acting in environments with the goal of maximising their shared utility. In these environments, agents must learn communication protocols in order to share information that is needed to solve the tasks. By embraci.. 2021. 7. 7. 이전 1 다음 반응형