View source on GitHub
|
A REINFORCE Agent.
Implements the REINFORCE algorithm from (Williams, 1992): https://www-anw.cs.umass.edu/~barto/courses/cs687/williams92simple.pdf
Classes
class ReinforceAgent: A REINFORCE Agent.
class ReinforceAgentLossInfo: ReinforceAgentLossInfo is stored in the extras field of the LossInfo.
Type Aliases
AdvantageFnType: The central part of internal API.