OpenAI 挑战《索尼克》,阿里南大队如何一举夺魁?(15)


个动作),结合官方提供的baseline和我们的经验,抽象了如下10个离散动作(actions),其中[]表示的不按任何键,对应的就是在游戏中等待,对应的操作在需要原地等待的关卡中非常有用。

buttons

= [

"B"

,

"A"

,

"MODE"

,

"START"

,

"UP"

,

"DOWN"

,

"LEFT"

,

"RIGHT"

,

"C"

,

"Y"

,

"X"

,

"Z"

]

actions

= [[

"LEFT"

], [

"RIGHT"

], [

"LEFT"

,

"DOWN"

], [

"RIGHT"