def estimation(self, time_step, main_sim, enemy_action_prob, types):
# For the unkown agents, estimating the parameters and types
loaded_items_list = self.find_loaded_item(main_sim)
for unknown_agent in self.visible_agents:
if unknown_agent is not None:
# 1. Selecting the types
parameter_estimation = unknown_agent.agents_parameter_estimation
if parameter_estimation.type_selection_mode == 'AS':
selected_types = types
if parameter_estimation.type_selection_mode == 'BS':
selected_types = parameter_estimation.UCB_selection(
time_step) # returns l1, l2, f1, f2,w
# 2. Defining the next agent action or appending the action
# for the history based method
if parameter_estimation.train_mode == 'history_based':
parameter_estimation.action_history.append(
unknown_agent.next_action)
if unknown_agent.next_action != 'L':
parameter_estimation.actions_to_reach_target.append(
unknown_agent.next_action)
# 3. Estimating
if unknown_agent.next_action is not None:
tmp_sim = copy(main_sim)
tmp_previous_state = copy(self.previous_state)
parameter_estimation.process_parameter_estimations(
unknown_agent, tmp_previous_state, tmp_sim,
enemy_action_prob, selected_types, loaded_items_list)
def estimation(self, time_step, main_sim, enemy_action_prob, types,
actions, current_state):
# For the unknown agents, estimating the parameters and types
loaded_items_list = self.find_loaded_item(main_sim)
for unknown_agent in self.agent_memory:
if unknown_agent is not None:
# 1. Selecting the types
parameter_estimation = unknown_agent.agents_parameter_estimation
if parameter_estimation.type_selection_mode == 'AS':
selected_types = types
if parameter_estimation.type_selection_mode == 'BS':
selected_types = parameter_estimation.UCB_selection(
time_step) # returns l1, l2, f1, f2,w
# 2. Defining the next agent action or appending the action
# for the history based method
if parameter_estimation.train_mode == 'history_based':
parameter_estimation.action_history.append(
unknown_agent.next_action)
if unknown_agent.next_action != 'L':
parameter_estimation.actions_to_reach_target.append(
unknown_agent.next_action)
# 3. Estimating
# print unknown_agent.next_action
if self.agent_is_visible(
unknown_agent
) and unknown_agent.next_action is not None:
tmp_sim = copy(main_sim)
tmp_previous_state = copy(self.previous_state)
parameter_estimation.process_parameter_estimations(
unknown_agent, tmp_previous_state, tmp_sim,
enemy_action_prob, selected_types, loaded_items_list,
True)
elif current_state is not None:
for agent in current_state.agents:
if agent.index == unknown_agent.index:
next_action = agent.next_action
break
previous_state = self.generate_previous_state(
unknown_agent, next_action, current_state)
unknown_agent.next_action = next_action
#parameter_estimation.unseen_parameter_estimation_not_update(unknown_agent,selected_types)
parameter_estimation.process_parameter_estimations(
unknown_agent, previous_state, current_state,
enemy_action_prob, selected_types, loaded_items_list,
True)
print "End of Estimationnnnnnnnn----------------------------------"