acrobot_vec_env.h

Go to the documentation of this file.

#ifndef ACROBOT_ENV_H
#define ACROBOT_ENV_H
 
#include "bitrl/bitrl_types.h"
#include "bitrl/envs/gymnasium/gymnasium_vector_env_base.h"
#include "bitrl/envs/space_type.h"
#include "bitrl/envs/vector_time_step.h"
#include "bitrl/extern/nlohmann/json/json.hpp"
#include "bitrl/network/rest_rl_env_client.h"
 
#include <any>
#include <string>
#include <vector>
 
namespace bitrl
{
 
template <typename StateTp> class VectorTimeStep;
 
namespace envs::gymnasium
{
 
namespace detail_
{
 
struct AcrobotVEnv
{
 
    typedef ContinuousVectorSpace<6, real_t> state_space;
 
    typedef state_space::space_item_type state_type;
 
    static constexpr uint_t STATE_SPACE_SIZE = state_space::size;
 
    typedef ScalarDiscreteSpace<0, 3> action_space;
 
    typedef std::vector<typename action_space::space_item_type> action_type;
 
    static constexpr uint_t ACTION_SPACE_SIZE = action_space::size;
};
 
} // namespace detail_
 
class AcrobotV final : public GymnasiumVecEnvBase<VectorTimeStep<detail_::AcrobotVEnv::state_type>,
                                                  detail_::AcrobotVEnv>
{
 
  public:
    static const std::string name;
 
    static const std::string URI;
 
    typedef GymnasiumVecEnvBase<VectorTimeStep<detail_::AcrobotVEnv::state_type>,
                                detail_::AcrobotVEnv>::base_type base_type;
 
    typedef typename base_type::time_step_type time_step_type;
 
    typedef typename base_type::state_space_type state_space_type;
 
    typedef typename base_type::action_space_type action_space_type;
 
    typedef typename base_type::action_type action_type;
 
    typedef typename base_type::state_type state_type;
 
    AcrobotV(network::RESTRLEnvClient &api_server);
 
    AcrobotV(const AcrobotV &other);
 
    ~AcrobotV() override = default;
 
    virtual void
    make(const std::string &version, const std::unordered_map<std::string, std::any> &,
         const std::unordered_map<std::string, std::any> &reset_options) override final;
 
    virtual time_step_type step(const action_type &action) override final;
 
    uint_t n_actions() const noexcept { return action_space_type::size; }
 
  protected:
    virtual time_step_type
    create_time_step_from_response_(const nlohmann::json &response) const override final;
};
 
} // namespace envs::gymnasium
} // namespace bitrl
 
#endif // PENDULUM_ENV_H