Home > marl > agent > actfuns > Contents.m

Contents

PURPOSE ^

Multiagent Reinforcement Learning toolbox

SYNOPSIS ^

This is a script file.

DESCRIPTION ^

 Multiagent Reinforcement Learning toolbox
 Version 1.0

 This directory contains action selection algorithm implementations

 act                   - Template. Chooses an action for the agent
 asfq_greedyact        - Deterministic greedy action selection for adaptive state focus Q-learning
 fullstate_greedyact   - Deterministic full-state greedy action selection
 fullstate_stochact    - Stochastic action selection for policy indexed on full world state
 greedyact             - Deterministic greedy action selection for Q-learners
 pigreedyact           - Greedy policy-based action selection for policy indexed on agent's state
 staticact             - Static (non-learning) action selection policies
 stochact              - Stochastic action selection for policy indexed on agent's state
 teamgreedyact         - Deterministic greedy action selection for full-state, joint action Q-learners

CROSS-REFERENCE INFORMATION ^

This function calls: This function is called by:
Generated on Wed 04-Aug-2010 16:55:08 by m2html © 2005