public SolverManager()
{
FG = 0;
_timestamp = DateTime.Now.ToFileTime();
_logger = new Logger();
#if !DEBUG
_logger.Init(".\\app_" + _timestamp + ".log");
#endif
_logger.Log(JsonConvert.SerializeObject(SolverConfig.GetInstance()));
int asyncLearners = SolverConfig.GetInstance().async_learners;
_actorMonitor = new Dictionary <int, int>();
_inputInterface = new InputInterface();
_encoder = new StateEncoder(_inputInterface);
_agent = new AsyncQN(asyncLearners);
_learners = new AsyncSolver[asyncLearners];
for (int i = 0; i < asyncLearners; i++)
{
IExploration exp = null;
exp = new BoltzmannExploration(SolverConfig.GetInstance().epsilon, 0.13f);
exp.Init(0.13f);
//exp = new EGreedyExploration(SolverConfig.GetInstance().epsilon, 0f);
//exp.Init(0.05f, 0f);
_learners[i] = new AsyncSolver(_inputInterface, _encoder, _agent, exp, _logger);
}
}
public Solver(InputInterface p_inputInterface, StateEncoder p_encoder, BaseAgent p_agent, IExploration p_exp, Logger p_logger)
{
_inputInterface = p_inputInterface;
_encoder = p_encoder;
_agent = p_agent;
_exploration = p_exp;
_logger = p_logger;
_gameState = new StateVar();
_histogram = new Dictionary <int, int>();
}
public void Start(IExploration p_exp)
{
_logger = new Logger();
_timestamp = DateTime.Now.ToFileTime();
#if !DEBUG
_logger.Init(".\\app_" + _timestamp + ".log");
#endif
_wins = _loses = 0;
_exp = p_exp;
_agent = new ACN();
_firstRun = true;
_environment = new FrozenLake();
Reset();
}
override public int ChooseAction(IExploration p_exp, Vector p_estimate)
{
_action = p_exp.ChooseAction(p_estimate);
/*
* BoltzmannExploration exp = (BoltzmannExploration)p_exp;
*
* for(int i = 0; i < 5; i++)
* {
* exp.Temperature = 0.5f * i + 0.15f;
* exp.ChooseAction(p_estimate);
* }
*/
return(_action);
}
override public int ChooseAction(IExploration p_exp, Vector p_estimate)
{
_action = p_exp.ChooseAction(p_estimate);
return(_action);
}
public AsyncSolver(InputInterface p_inputInterface, StateEncoder p_encoder, BaseAgent p_agent, IExploration p_exp, Logger p_logger) : base(p_inputInterface, p_encoder, p_agent, p_exp, p_logger)
{
}
virtual public int ChooseAction(IExploration p_exp, Vector p_state0)
{
return(0);
}
