observation = env.reset()
ep_r = 0
while True:
env.render()
action = RL.choose_action(observation)
observation_, reward, done, info = env.step(action)
position, velocity = observation_
reward = abs(position - (-0.5)) # r in [0, 1]
RL.store_transition(observation, action, reward, observation_)
ep_r += reward
if total_steps > 1000:
RL.learn()
if done:
get = '| Get' if observation_[
0] >= env.unwrapped.goal_position else '| ----'
print('Epi: ', i_episode, get, '| Ep_r: ', round(ep_r, 4),
'| Epsilon: ', round(RL.epsilon, 2))
break
observation = observation_
total_steps += 1
RL.plot_cost()
# break while loop when end of this episode
if done:
print('game over')
print(env.balance)
break
step += 1
# end of game
#env.destroy()
if __name__ == "__main__":
# maze game
env = FX()
DQN = DQN(
env.n_actions,
env.n_features,
learning_rate=0.01,
reward_decay=0.9,
e_greedy=0.9,
replace_target_iter=200,
memory_size=2000,
# output_graph=True
)
# env.after(100, run_maze)
run_maze()
# env.mainloop()
DQN.plot_cost()