in envs/thor_beacons.py [0:0]
def step(self, action):
obs, rewards, done, info = super().step(action)
# place beacon for interaction
if info['action'] in self.interaction_set and info['target'] is not None:
target = info['target']['objectId'] or info['target']['center_objectId']
if target is not None:
self.beacons.append({'t':self.t-1, 'target':target, 'action':info['action'], 'success':info['success']})
hist = self.compile_history(self.state)
self.history.append({'t':self.t-1, **hist})
# if final timestep, then compute masks for the entire trajectory and add to info
if self.t==self.max_t:
info['traj_masks'] = self.compute_masks()
return obs, rewards, done, info