Prior knowledge based reinforcement learning system 基于先驗(yàn)知識(shí)的強(qiáng)化學(xué)習(xí)系統(tǒng)
In recent years , reinforcement learning has become one of the key research areas in artificial intelligence and machine learning and it has attracted many researchers in other fields including operations research , control theory and robotics . reinforcement learning is different from supervised learning in that no teacher signals are needed and a reinforcement learning system learns by interacting with the environment to maximize the evaluative feedback from the environment 增強(qiáng)學(xué)習(xí)與監(jiān)督學(xué)習(xí)的不同之處在于,增強(qiáng)學(xué)習(xí)不要求給定各種狀態(tài)下的期望輸出即教師信號(hào),而強(qiáng)調(diào)在與環(huán)境交互中的學(xué)習(xí),以極大(或極小)化從環(huán)境獲得的評(píng)價(jià)性反饋信號(hào)為學(xué)習(xí)目標(biāo)。