8b83832156fd8f11cc4f97603d17c85191627120,examples/theano/ddpg_cartpole.py,,run_task,#,11

Before Change

def run_task(*_):
    env = normalize(CartpoleEnv())

    policy = DeterministicMLPPolicy(
        env_spec=spec(env),
        // The neural network policy should have two hidden layers, each with 32 hidden units.
        hidden_sizes=(32, 32))

    es = OUStrategy(env_spec=spec(env))

    qf = ContinuousMLPQFunction(env_spec=spec(env))

    algo = DDPG(
        env=env,

After Change

def run_task(*_):
    env = TheanoEnv(normalize(CartpoleEnv()))

    policy = DeterministicMLPPolicy(
        env_spec=env.spec,
        // The neural network policy should have two hidden layers,
        // each with 32 hidden units.
        hidden_sizes=(32, 32))

    es = OUStrategy(env_spec=env.spec)

    qf = ContinuousMLPQFunction(env_spec=env.spec)

    algo = DDPG(
        env=env,

Instances