Uses of Class
net.pakl.rl.Agent

Packages that use Agent

net.pakl.rl

These are the basic reinforcement learning model classes -- every reinforcement learning problem can be described (minimally) as a World (collection of states), Policy, ValueFunction, and Actions.

Uses of Agent in net.pakl.rl

Subclasses of Agent in net.pakl.rl

class

AgentParallelized This class represents a multi-threaded agent (therefore faster if you have multiple CPUs) appropriate for reinforcement learning with full Value Iteration, since during value iteration each state can be updated independently of others (as long as testTrainSameVf is false).