[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fin4MqY-docGH9z00ylWSserwRTdooUvzyJODBYs4Qr0":3},{"answer":4,"createTime":5,"id":6,"options":7,"origin":12,"question":19,"related":20,"source":30,"type":44},[],"2023-11-27 12:03:58",108986325,[8,9,10,11],"监督学习","非监督学习","强化学习","线性回归",{"count":13,"courseId":14,"courseImg":15,"courseName":16,"workId":17,"workName":18},12,"306d47969b59e6f36470c235ae597dac","https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002F151b1e04e0edd24518d87450e76e122a.jpg","人工智能与信息社会","ae4aef4d7f5a4e9386df663935ef3991","第六章","典型的"鸡尾酒会"问题中,提取出不同人说话的声音是属于()",[21,32,41,45,50,59,68,77,82,91],{"answer":22,"createTime":23,"id":24,"options":25,"question":29,"source":30,"type":31},[],"2023-11-27 12:03:57",108986318,[26,27,28,11],"支持向量机","决策树","神经网络","用于监督分类的算法有()","v1",1,{"answer":33,"createTime":23,"id":34,"options":35,"question":40,"source":30,"type":31},[],108986323,[36,37,38,39],"状态","动作","回报","强化","在强化学习中,主体和环境之间交互的要素有()",{"answer":42,"createTime":5,"id":6,"options":43,"question":19,"source":30,"type":44},[],[8,9,10,11],0,{"answer":46,"createTime":5,"id":47,"options":48,"question":49,"source":30,"type":44},[],108986328,[8,9,10,11],"()有跟环境进行交互,从反馈当中进行不断的学习的过程",{"answer":51,"createTime":5,"id":52,"options":53,"question":58,"source":30,"type":44},[],108986330,[54,55,56,57],"状态动作函数","状态值函数","动作值函数","策略函数","在Q-Learning中,所谓的Q函数是指()",{"answer":60,"createTime":5,"id":61,"options":62,"question":67,"source":30,"type":44},[],108986333,[63,64,65,66],"期望值","最大值","最小值","总和","Q函数Q(s,a)是指在一个给定状态s下,采取某一个动作a之后,后续的各个状态所能得到的回报的()",{"answer":69,"createTime":5,"id":70,"options":71,"question":76,"source":30,"type":44},[],108986337,[72,73,74,75],"大;小","大;大","小;小","小;大","在强化学习的过程中,学习率α越大,表示采用新的尝试得到的结果比例越(),保持旧的结果的比例越()",{"answer":78,"createTime":5,"id":79,"options":80,"question":81,"source":30,"type":44},[],108986339,[72,73,74,75],"在ε-greedy策略当中,ε的值越大,表示采用随机的一个动作的概率越(),采用当前Q函数值最大的动作的概率越()",{"answer":83,"createTime":5,"id":84,"options":85,"question":90,"source":30,"type":44},[],108986342,[86,87,88,89],"探索;开发","开发;探索","探索;输出","开发;输出","在强化学习过程中,()表示随机地采取某个动作,以便于尝试各种结果;()表示采取当前认为最优的动作,以便于进一步优化评估当前认为最优的动作的值",{"answer":92,"createTime":5,"id":93,"options":94,"question":99,"source":30,"type":44},[],108986344,[95,96,97,98],"探索","开发","输入","输出","强化学习中,()主要探索未知的动作会产生的效果,有利于更新Q值,获得更好的策略"]