testingNeat

#include <iostream>
#include <mlpack/methods/neat/neat.hpp>
#include "environment.hpp"

using namespace gym;
using namespace mlpack::neat;

class GymTask
{
 public:
	GymTask()
	{ /* Nothing to do here */ }

	double Evaluate(Genome<> genome)
	{
		const std::string environment = "CartPole-v0";
	  const std::string host = "127.0.0.1";
	  const std::string port = "4040";

	  double totalReward = 0;
	  size_t totalSteps = 0;

	  Environment env(host, port, environment);
	  arma::mat observation = env.reset();

	  while (1)
	  {
	  	arma::vec input = {observation(0, 0), observation(1, 0), observation(2, 0), observation(3, 0)};
	    arma::vec output = genome.Evaluate(input);
	    output = arma::clamp(output, 0, 1);
	    output[0] = std::round(output[0]);
	    arma::mat action(output);
	    env.step(action);

	    observation = env.observation;

	    if (env.done)
	    	break;
	    totalReward += env.reward;
	    totalSteps += 1;
	  }

	  std::cout << "Instance: " << env.instance << " total steps: " << totalSteps
      << " reward: " << totalReward << std::endl;

	  return totalReward;
	}

	double EvaluateWithVid(Genome<> genome)
	{
		const std::string environment = "CartPole-v0";
	  const std::string host = "127.0.0.1";
	  const std::string port = "4040";

	  double totalReward = 0;
	  size_t totalSteps = 0;

	  Environment env(host, port, environment);
		env.compression(0);
	  env.monitor.start("./dummy/", true, true);

	  arma::mat observation = env.reset();
	  env.render();

	  while (1)
	  {
	  	arma::vec input = {observation(0, 0), observation(1, 0), observation(2, 0), observation(3, 0)};
	    arma::vec output = genome.Evaluate(input);
	    output = arma::clamp(output, 0, 1);
	    output[0] = std::round(output[0]);
	    arma::mat action(output);
	    env.step(action);

	    if (env.done)
	    	break;

	    observation = env.observation;

	    totalReward += env.reward;
	    totalSteps += 1;
	    std::cout << "Current step: " << totalSteps << " current reward: "
	      << totalReward << std::endl;
	  }

	  std::cout << "Instance: " << env.instance << " total steps: " << totalSteps
      << " reward: " << totalReward << std::endl;

    std::cout << "Video: https://kurg.org/media/gym/" << env.instance
      << " (it might take some minutes before the video is accessible)."
      << std::endl;

	  return totalReward;
	}
};

int main(int argc, char* argv[])
{
  GymTask task;
  NEAT<GymTask> model(task, 4, 1, 100, 20, 10);

  Genome<> bestGenome = model.Train();
	double finalFitness = task.EvaluateWithVid(bestGenome);
	std::cout << finalFitness << std::endl;
	return 0;
}