def env_agent_config(cfg, seed=1):
env = RacetrackEnv()
action_dim = 9
agent = FisrtVisitMC(action_dim, cfg)
return env, agent
ep_reward += reward
one_ep_transition.append((state, action, reward))
state = next_state
if done:
break
rewards.append(ep_reward)
if ma_rewards:
ma_rewards.append(ma_rewards[-1] * 0.9 + ep_reward * 0.1)
else:
ma_rewards.append(ep_reward)
agent.update(one_ep_transition)
if (i_episode + 1) % 10 == 0:
print("Episode:{}/{}: Reward:{}".format(i_episode + 1,
mc_cfg.n_episodes,
ep_reward))
return rewards, ma_rewards
if __name__ == "__main__":
mc_cfg = MCConfig()
env = RacetrackEnv()
n_actions = 9
agent = FisrtVisitMC(n_actions, mc_cfg)
rewards, ma_rewards = mc_train(mc_cfg, env, agent)
save_results(rewards, ma_rewards, tag='train', path=RESULT_PATH)
plot_rewards(rewards,
ma_rewards,
tag="train",
algo="On-Policy First-Visit MC Control",
path=RESULT_PATH)
def env_agent_config(cfg, seed=1):
env = RacetrackEnv()
action_dim = 9
agent = Sarsa(action_dim, cfg)
return env, agent