Function play_one_episode

tf2.0/mlp_trader.py:313–328

(agent, env, is_train)

def play_one_episode(agent, env, is_train):
  # note: after transforming states are already 1xD
  state = env.reset()
  state = scaler.transform([state])
  done = False

  while not done:
    action = agent.act(state)
    next_state, reward, done, info = env.step(action)
    next_state = scaler.transform([next_state])
    if is_train == 'train':
      agent.update_replay_memory(state, action, reward, next_state, done)
      agent.replay(batch_size)
    state = next_state

  return info['cur_val']