Env Demo

class DemoEnv(ParallelEnv):
    metadata = {
        "name": "demo_env",
    }

    def __init__(self, set_seed=42):
        self.REFRESH_RATE = 240
        self.dt = 1 / self.REFRESH_RATE

        # Team 1
        self.player1 = Player([1000, 1000], [0, -1], 0, Shotgun(self.REFRESH_RATE))
        self.player2 = Player([2000, 1000], [0, -1], 0, AssaultRifle(self.REFRESH_RATE)
        )
        self.player3 = Player([3000, 1000], [0, -1], 0, SniperRifle(self.REFRESH_RATE)
        )

        # Team 2
        self.player4 = Player([3000, 3000], [0, 1], 1, Shotgun(self.REFRESH_RATE))
        self.player5 = Player([2000, 3000], [0, 1], 1, AssaultRifle(self.REFRESH_RATE))
        self.player6 = Player([1000, 3000], [0, 1], 1, SniperRifle(self.REFRESH_RATE))

        # Contains all of the players in the game
        self.players = [self.player1, self.player2, self.player3, self.player4, self.player5, self.player6]

        #Blocks
        self.block1 = Block([1500, 2000], 200, 1200)
        self.block2 = Block([2500, 2000], 200, 1200)
        self.block3 = Block([1000, 2000], 400, 400)
        self.block4 = Block([2000, 2000], 400, 400)
        self.block5 = Block([3000, 2000], 400, 400)

        #List of all blocks
        self.blocks = [self.block1, self.block2, self.block3, self.block4, self.block5]

        #Set countdowns
        self.countdowns = {p: 0 for p in self.players}

        #Access player object using string
        self.playerLabel = {"player1": self.player1,
                            "player2": self.player2,
                            "player3": self.player3,
                            "player4": self.player4,
                            "player5": self.player5,
                            "player6": self.player6,
        }

        #Access player string using player object
        self.invPlayerLabels = {self.player1: "player1",
                                self.player2: "player2",
                                self.player3: "player3",
                                self.player4: "player4",
                                self.player5: "player5",
                                self.player6: "player6",
        }

        #Player strings
        self.possible_agents = ["player1", "player2", "player3", "player4", "player5", "player6"]

        #Current timestep
        self.timesteps = 0

        #Max timesteps in a game
        self.max_timestep = 6000

        self.scores = {0: 0,
                       1: 0}

        self.max_score = 600

        #self.num_agents = 6
        #self.max_num_agents = 6

        self.agents = copy(self.possible_agents)


        # obs_space = flatten_space(Dict({
        #     "distances": Box(low=0, high=1, shape=(8,), dtype=np.float32),
        #     "healths": Box(low=0, high=100, shape=(8,), dtype='i'),
        #     "alliances": Box(low=-1, high=1, shape=(8,), dtype='i'),
        #     "player_health": Discrete(101, start=0),
        #     "can_fire": MultiBinary(1),
        # }), )

        low_obs = [0] * 8 + [0] * 8 + [-1]*8 + [0] + [0]
        high_obs = [1] * 8 + [100] * 8 + [1]*8 + [100] + [1]

        obs_space = Box(low=np.array(low_obs), high=np.array(high_obs), shape=(26,), dtype=np.float32)

        self.observation_spaces = {a: obs_space for a in self.agents}

        # action_space = flatten_space(Dict({
        #     "forward": Box(low=-1, high=1, shape=(1,), dtype=np.float32),
        #     "right": Box(low=-1, high=1, shape=(1,), dtype=np.float32),
        #     "rot_rate": Box(low=-pi, high=pi, shape=(1,), dtype=np.float32),
        #     "firing": MultiBinary(1),
        # }))

        low_act = [-1, -1, -pi, 0]
        high_act = [1, 1, pi, 1]

        action_space = Box(low=np.array(low_act), high=np.array(high_act), shape=(4,), dtype=np.float32)

        self.action_spaces = {a: action_space for a in self.agents}