INNER CODE UNIT · Python
max_value
rlcode/reinforcement-learning · 1-grid-world/2-value_iteration.py:33
max_value = -99999
if state == [2, 2]:
return []
# calculating q values for the all actions and
# append the action to action list which has maximum q value
for action in self.env.possible_actions:
next_state = self.env.state_after_action(state, action)
reward = self.env.get_reward(state, action)
next_value = self.get_value(next_state)
value = (reward + self.discount_factor * next_value)
if value > max_value:
action_list.clear()
action_list.append(action)
max_value = value