[QUESTION] Stable Baseline render vectorized forex enviroment about gym-anytrading HOT 8 CLOSED

env_maker = lambda: gym.make('forex-v0', frame_bound=(100, 5000), window_size=10)
env = DummyVecEnv([env_maker])

# Training Env
policy_kwargs = dict(net_arch=[64, 'lstm',dict(vf=[128,128,128], pi=[64,64])])
model = A2C("MlpLstmPolicy", env, verbose=1, policy_kwargs=policy_kwargs)
model.learn(total_timesteps=1000)

# Testing Env 
env = env_maker()
observation = env.reset()

while True:
    observation = observation[np.newaxis, ...]
    # action = env.action_space.sample()
    action, _states = model.predict(observation)
    observation, reward, done, info = env.step(action)
    # env.render()
    if done:
        print("info:", info)
        break

# Plotting results
plt.cla()
env.render_all()
plt.show()

env = DummyVecEnv([lambda: gym.make('forex-v0', frame_bound=(100, 5000), window_size=10)])

# Training Env
policy_kwargs = dict(net_arch=[64, 'lstm',dict(vf=[128,128,128], pi=[64,64])])
model = A2C("MlpLstmPolicy", env, verbose=1, policy_kwargs=policy_kwargs)
model.learn(total_timesteps=1000)

# Testing Env 
observation = env.reset()
while True:
    # action = env.action_space.sample()
    action = model.predict(observation)
    observation, reward, done, info = env.step(action)
    # env.render()
    if done:
        print("info:", info)
        break

# Plotting results
plt.cla()
env.envs[0].render_all()
plt.show()