mountain_car.hpp

Go to the documentation of this file.

#ifndef MLPACK_METHODS_RL_ENVIRONMENT_MOUNTAIN_CAR_HPP
#define MLPACK_METHODS_RL_ENVIRONMENT_MOUNTAIN_CAR_HPP

#include <mlpack/prereqs.hpp>

namespace mlpack {
namespace rl {

class MountainCar
{
 public:
  class State
  {
   public:
    State(): data(dimension, arma::fill::zeros)
    { /* Nothing to do here. */ }

    State(const arma::colvec& data): data(data)
    { /* Nothing to do here. */ }

    arma::colvec& Data() { return data; }

    double Velocity() const { return data[0]; }
    double& Velocity() { return data[0]; }

    double Position() const { return data[1]; }
    double& Position() { return data[1]; }

    const arma::colvec& Encode() const { return data; }

    static constexpr size_t dimension = 2;

   private:
    arma::colvec data;
  };

  enum Action
  {
    backward,
    stop,
    forward,

    size
  };

  MountainCar(const double positionMin = -1.2,
              const double positionMax = 0.5,
              const double velocityMin = -0.07,
              const double velocityMax = 0.07,
              const double doneReward = 0) :
      positionMin(positionMin),
      positionMax(positionMax),
      velocityMin(velocityMin),
      velocityMax(velocityMax),
      doneReward(doneReward)
  { /* Nothing to do here */ }

  double Sample(const State& state,
                const Action& action,
                State& nextState) const
  {
    // Calculate acceleration.
    int direction = action - 1;
    nextState.Velocity() = state.Velocity() + 0.001 * direction - 0.0025 *
        std::cos(3 * state.Position());
    nextState.Velocity() = std::min(
        std::max(nextState.Velocity(), velocityMin), velocityMax);

    // Update states.
    nextState.Position() = state.Position() + nextState.Velocity();
    nextState.Position() = std::min(
        std::max(nextState.Position(), positionMin), positionMax);

    if (std::abs(nextState.Position() - positionMin) <= 1e-5)
    {
      nextState.Velocity() = 0.0;
    }
    bool done = IsTerminal(nextState);
    if (done)
      return doneReward;
    return -1.0;
  }

  double Sample(const State& state, const Action& action) const
  {
    State nextState;
    return Sample(state, action, nextState);
  }

  State InitialSample() const
  {
    State state;
    state.Velocity() = 0.0;
    state.Position() = arma::as_scalar(arma::randu(1)) * 0.2 - 0.6;
    return state;
  }

  bool IsTerminal(const State& state) const
  {
    return std::abs(state.Position() - positionMax) <= 1e-5;
  }

 private:
  double positionMin;

  double positionMax;

  double velocityMin;

  double velocityMax;

  double doneReward;
};

} // namespace rl
} // namespace mlpack

#endif