QLearning.java 文件源码

/**
 * Returns the {@link QLearningStateNode} object stored for the given hashed state. If no {@link QLearningStateNode} object.
 * is stored, then it is created and has its Q-value initialize using this objects {@link burlap.behavior.valuefunction.ValueFunctionInitialization} data member.
 * @param s the hashed state for which to get the {@link QLearningStateNode} object
 * @return the {@link QLearningStateNode} object stored for the given hashed state. If no {@link QLearningStateNode} object.
 */
protected QLearningStateNode getStateNode(HashableState s){

    QLearningStateNode node = qIndex.get(s);

    if(node == null){
        node = new QLearningStateNode(s);
        List<GroundedAction> gas = this.getAllGroundedActions(s.s);
        if(gas.size() == 0){
            gas = this.getAllGroundedActions(s.s);
            throw new RuntimeErrorException(new Error("No possible actions in this state, cannot continue Q-learning"));
        }
        for(GroundedAction ga : gas){
            node.addQValue(ga, qInitFunction.qValue(s.s, ga));
        }

        qIndex.put(s, node);
    }

    return node;

}