[英]How does the is_slippery parameter affect the reward in Frozenlake Environment?
How does the is_slippery parameter affect the reward in Frozenlake Environment? is_slippery 参数如何影响 Frozenlake 环境中的奖励?
Frozenlake environment has a parameter named is_slippery, which if set to True will move in intended direction with probability of 1/3 else will move in either perpendicular direction with equal probability of 1/3 in both directions. Frozenlake 环境有一个名为 is_slippery 的参数,如果设置为 True,它将以 1/3 的概率沿预期方向移动,否则将以 1/3 的相等概率在两个方向上沿任一垂直方向移动。 How does this is_slippery parameter affect the reward generated from the environment?
这个 is_slippery 参数如何影响环境产生的奖励? Or does it merely do the job of deflecting the agent from it intended path?
或者它只是做使代理偏离其预期路径的工作?
The "is_slippery" parameter determines if you are using the Frozenlake environment as stochastic (True) or deterministic (False). “is_slippery”参数确定您是使用 Frozenlake 环境作为随机 (True) 还是确定性 (False)。
However, the Frozen Lake environment can also be used in deterministic mode.
但是,Frozen Lake 环境也可以在确定性模式下使用。 By setting the property is_slippery=False when creating the environment, the slippery surface is turned off and then the environment always executes the action chosen by the agent.
通过在创建环境时设置属性 is_slippery=False ,关闭滑面,然后环境始终执行代理选择的动作。
https://zoo.cs.yale.edu/classes/cs470/materials/hws/hw7/FrozenLake.html https://zoo.cs.yale.edu/classes/cs470/materials/hws/hw7/FrozenLake.html
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.