steffen/marl-factory-grid
1
0
Fork 0
mirror of https://github.com/illiumst/marl-factory-grid.git synced 2025-05-23 15:26:43 +02:00
Code Issues Packages Projects Releases Wiki Activity

updated base factory

Browse Source
This commit is contained in:
romue 2021-05-10 10:50:45 +02:00
parent ed10b3225d
commit a4a4ab067e
2 changed files with 11 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
environments/factory/base_factory.py
View File

@ -45,19 +45,16 @@ class BaseFactory(object):
collisions_vec = self.state[:, x, y].copy() # otherwise you overwrite the grid/state collisions_vec = self.state[:, x, y].copy() # otherwise you overwrite the grid/state
collisions_vec[i+1] = 0 # no self-collisions collisions_vec[i+1] = 0 # no self-collisions
collision_vecs.append(collisions_vec) collision_vecs.append(collisions_vec)
self.handle_collisions(collisions_vec) reward, info = self.step_core(collisions_vec, actions, r)
r += self.step_core(collisions_vec, actions, r) r += reward
if self.steps >= self.max_steps: if self.steps >= self.max_steps:
self.done = True self.done = True
return self.state, r, self.done, {} return self.state, r, self.done, info
def make_move(self, agent_i, old_pos, new_pos): def make_move(self, agent_i, old_pos, new_pos):
(x, y), (x_new, y_new) = old_pos, new_pos (x, y), (x_new, y_new) = old_pos, new_pos
self.state[agent_i+1, x, y] = 0 self.state[agent_i+1, x, y] = 0
self.state[agent_i+1, x_new, y_new] = 1 self.state[agent_i+1, x_new, y_new] = 1
def handle_collisions(self, vecs):
pass
def step_core(self, collisions_vec, actions, r): def step_core(self, collisions_vec, actions, r):
return 0 return 0, {}

10
environments/factory/simple_factory.py
View File

@ -11,13 +11,17 @@ class SimpleFactory(BaseFactory):
super().reset() super().reset()
dirt_slice = np.zeros((1, *self.state.shape[1:])) dirt_slice = np.zeros((1, *self.state.shape[1:]))
self.state = np.concatenate((self.state, dirt_slice)) # dirt is now the last slice self.state = np.concatenate((self.state, dirt_slice)) # dirt is now the last slice
free_for_dirt = self.state.sum(0) free_for_dirt = self.free_for_dirt()
free_for_dirt = np.argwhere(free_for_dirt == 0)
np.random.shuffle(free_for_dirt)
for x, y in free_for_dirt[:self.max_dirt]: for x, y in free_for_dirt[:self.max_dirt]:
self.state[-1, x, y] = 1 self.state[-1, x, y] = 1
print(self.state) print(self.state)
def free_for_dirt(self):
free_for_dirt = self.state.sum(0)
free_for_dirt = np.argwhere(free_for_dirt == 0)
np.random.shuffle(free_for_dirt)
return free_for_dirt
if __name__ == '__main__': if __name__ == '__main__':
factory = SimpleFactory(n_agents=1, max_dirt=8) factory = SimpleFactory(n_agents=1, max_dirt=8)