cliff_world_env.h

Go to the documentation of this file.

#ifndef CLIFF_WORLD_H
#define CLIFF_WORLD_H
 
#include "bitrl/bitrl_types.h"
#include "bitrl/envs/gymnasium/toy_text/toy_text_base.h"
#include "bitrl/envs/time_step.h"
#include "bitrl/extern/nlohmann/json/json.hpp"
#include "bitrl/network/rest_rl_env_client.h"
 
#include <any>
#include <string>
#include <tuple>
#include <unordered_map>
 
namespace bitrl
{
namespace envs::gymnasium
{
 
class CliffWorld final : public ToyTextEnvBase<TimeStep<uint_t>, 37, 4>
{
 
  public:
    static const std::string name;
 
    static const std::string URI;
 
    typedef std::vector<std::tuple<real_t, uint_t, real_t, bool>> dynamics_type;
 
    typedef typename ToyTextEnvBase<TimeStep<uint_t>, 37, 4>::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;
 
    CliffWorld(network::RESTRLEnvClient &api_server);
 
    CliffWorld(const CliffWorld &other);
 
    ~CliffWorld() = default;
 
    virtual void
    make(const std::string &version, const std::unordered_map<std::string, std::any> &options,
         const std::unordered_map<std::string, std::any> &reset_options) override final;
 
    virtual time_step_type step(const action_type &action) override final;
 
  protected:
    uint_t max_episode_steps_;
 
    virtual time_step_type
    create_time_step_from_response_(const nlohmann::json &response) const override final;
};
 
} // namespace envs::gymnasium
} // namespace bitrl
#endif // CLIFF_WORLD_H