getStateValues

<p>[<code>matrix</code>]  Action value matrix.</p>

action.vals

<p>Get state value function from  action value function.</p>

Implements reinforcement learning environments and algorithms as described in Sutton & Barto (1998, ISBN:0262193981).
The Q-Learning algorithm can be used with function approximation,
eligibility traces (Singh & Sutton (1996) <doi:10.1007/BF00114726>)
and experience replay (Mnih et al. (2013) <arXiv:1312.5602>).

Markus Dumke

getStateValues: Get state values.

Description

Usage

Arguments