# Play from the command line against the trained agent
# in an actual (non-RLlib-wrapped) open-spiel env.
human_player = 1
env = Environment(args.env)
while num_episodes < args.num_episodes_human_play:
print("You play as {}".format("o" if human_player else "x"))
time_step = env.reset()
while not time_step.last():
player_id = time_step.observations["current_player"]
if player_id == human_player:
action = ask_user_for_action(time_step)
else:
obs = np.array(
time_step.observations["info_state"][player_id])
action = trainer.compute_single_action(obs,
policy_id="main")
# In case computer chooses an invalid action, pick a
# random one.
legal = time_step.observations["legal_actions"][player_id]
if action not in legal:
action = np.random.choice(legal)
time_step = env.step([action])
print(f"\n{env.get_state}")
print(f"\n{env.get_state}")
print("End of game!")
if time_step.rewards[human_player] > 0:
print("You win")
elif time_step.rewards[human_player] < 0:
print("You lose")
trainer.restore(checkpoint_path)
# Inference loop.
env = StatelessCartPole()
# Run manual inference loop for n episodes.
for _ in range(10):
episode_reward = 0.0
reward = 0.0
action = 0
done = False
obs = env.reset()
while not done:
# Create a dummy action using the same observation n times,
# as well as dummy prev-n-actions and prev-n-rewards.
action, state, logits = trainer.compute_single_action(
input_dict={
"obs": obs,
"prev_n_obs": np.stack([obs for _ in range(num_frames)]),
"prev_n_actions": np.stack([0 for _ in range(num_frames)]),
"prev_n_rewards": np.stack(
[1.0 for _ in range(num_frames)]),
},
full_fetch=True)
obs, reward, done, info = env.step(action)
episode_reward += reward
print(f"Episode reward={episode_reward}")
ray.shutdown()
# Train for n iterations and report results (mean episode rewards).
# Since we have to move at least 19 times in the env to reach the goal and
# each move gives us -0.1 reward (except the last move at the end: +1.0),
# we can expect to reach an optimal episode reward of -0.1*18 + 1.0 = -0.8
for i in range(5):
results = trainer.train()
print(f"Iter: {i}; avg. reward={results['episode_reward_mean']}")
# Perform inference (action computations) based on given env observations.
# Note that we are using a slightly different env here (len 10 instead of 20),
# however, this should still work as the agent has (hopefully) learned
# to "just always walk right!"
env = SimpleCorridor({"corridor_length": 10})
# Get the initial observation (should be: [0.0] for the starting position).
obs = env.reset()
done = False
total_reward = 0.0
# Play one episode.
while not done:
# Compute a single action, given the current observation
# from the environment.
action = trainer.compute_single_action(obs)
# Apply the computed action in the environment.
obs, reward, done, info = env.step(action)
# Sum up rewards for reporting purposes.
total_reward += reward
# Report results.
print(f"Played 1 episode; total-reward={total_reward}")
# __quick_start_end__
