class BotAgent:
def __init__(self, env):
"""An agent based on a GOFAI bot."""
self.env = env
self.on_reset()
def on_reset(self):
self.bot = Bot(self.env)
def act(self, obs=None, update_internal_state=True, *args, **kwargs):
action = self.bot.get_action()
if update_internal_state:
self.bot.take_action(action)
return {'action': action}
def analyze_feedback(self, reward, done):
pass
if options.verbose:
print(
'%s/%s: %s, seed=%d' %
(run_no + 1, options.num_runs, mission.surface, mission_seed))
optimal_actions = []
before_optimal_actions = []
non_optimal_steps = options.non_optimal_steps or int(
mission.max_steps // 3)
rng = Random(mission_seed)
try:
episode_steps = 0
while True:
action = expert.get_action()
if options.advise_mode and episode_steps < non_optimal_steps:
if rng.random() < options.bad_action_proba:
while True:
action = bad_agent.act(
mission.gen_obs())['action'].item()
# To make things simple, only allow random left/right/fwd moves, and opening of doors
if action in (mission.actions.left,
mission.actions.right,
mission.actions.forward):
break
fwd_pos = mission.agent_pos + mission.dir_vec
fwd_cell = mission.grid.get(*fwd_pos)
if action == mission.actions.toggle and fwd_cell is not None and fwd_cell.type == 'door':
break
