YannBerthelot

import math
from math import cos, sin, ceil, floor
import numpy as np
from numpy import arcsin
from numpy.linalg import norm
from .graph_utils import plot_duo, plot_multiple, plot_xy


class FlightModel:
    def __init__(self):

YannBerthelot

class CustomEnvironment(Environment):

    def __init__(self):
        super().__init__()

    def states(self):
        return dict(type='float', shape=(8,))

    def actions(self):
        return dict(type='int', num_values=4)

YannBerthelot

def states(self):
        return dict(type="float", shape=(4,))

YannBerthelot

    def states(self):
        return dict(type="float", shape=(self.STATES_SIZE,)) #self.STATES_SIZE = 4

    def actions(self):
        return {
            "thrust": dict(type="int", num_values=self.NUM_THRUST), #self.NUM_THRUST = 6 (50,60,70,80,90,100)
            "theta": dict(type="int", num_values=self.NUM_THETA), #self.NUM_THETA = 16 (from 0 to 15°)
        }

YannBerthelot

    def states(self):
        return dict(type="float", shape=(4,))

    def actions(self):
        return {
            "thrust": dict(type="int", num_values=6)
            "theta": dict(type="int", num_values=16)
        }
        

YannBerthelot

def max_episode_timesteps(self):
        return 100
def terminal(self):
        self.finished = self.FlightModel.Pos[1] > 25 # The Agent suceeded
        self.episode_end = (self.FlightModel.timestep > self.max_step_per_episode) or (
            self.FlightModel.Pos[0] > 5000 # The Agent did not suceed (runs of the runway or takes too much time)
        )
        return self.finished or self.episode_end

YannBerthelot

    def reward(self):
        if self.finished:
            reward = np.log(((5000 - self.FlightModel.Pos[0]) ** 2)) #if sucessfull reward based on how much runway is left (5000 being the length of the runway).
        else:
            reward = -1 #else, if unsucessful, give a small punition.
        return reward

YannBerthelot

    def execute(self, actions):
        next_state = self.FlightModel.compute_timestep(actions)
        terminal = self.terminal()
        reward = self.reward()
        return next_state, terminal, reward

YannBerthelot

def execute(self, actions):
        next_state = self.FlightModel.compute_timestep(actions) #defined in our AirplaneModel, see below
        terminal = self.terminal() #defined earlier
        reward = self.reward() #defined earlier
        return next_state, terminal, reward

YannBerthelot

from .FlightModel import FlightModel
import numpy as np
from tensorforce.environments import Environment


class PlaneEnvironment(Environment):
    def __init__(self):
        super().__init__()
        self.FlightModel = FlightModel()
        self.NUM_ACTIONS = len(self.FlightModel.action_vec)