rng = np.random.RandomState()
# --- Instantiate environment ---
env = Toy_env(rng)
# --- Instantiate qnetwork ---
qnetwork = MyQNetwork(env, parameters.rms_decay, parameters.rms_epsilon,
parameters.momentum, parameters.clip_delta,
parameters.freeze_interval, parameters.batch_size,
parameters.network_type, parameters.update_rule,
parameters.batch_accumulator, rng)
# --- Instantiate agent ---
agent = NeuralAgent(
env, qnetwork, parameters.replay_memory_size,
max(env.inputDimensions()[i][0]
for i in range(len(env.inputDimensions()))), parameters.batch_size,
rng)
# --- Bind controllers to the agent ---
# Before every training epoch (periodicity=1), we want to print a summary of the agent's epsilon, discount and
# learning rate as well as the training epoch number.
agent.attach(bc.VerboseController(evaluateOn='epoch', periodicity=1))
# During training epochs, we want to train the agent after every [parameters.update_frequency] action it takes.
# Plus, we also want to display after each training episode (!= than after every training) the average bellman
# residual and the average of the V values obtained during the last episode, hence the two last arguments.
agent.attach(
bc.TrainerController(evaluateOn='action',
periodicity=parameters.update_frequency,
showEpisodeAvgVValue=True,
env = Toy_env(rng)
# --- Instantiate qnetwork ---
qnetwork = MyQNetwork(env, parameters.rms_decay, parameters.rms_epsilon,
parameters.momentum, parameters.clip_norm,
parameters.freeze_interval, parameters.batch_size,
parameters.update_rule, rng)
train_policy = EpsilonGreedyPolicy(qnetwork, env.nActions(), rng, 0.1)
test_policy = EpsilonGreedyPolicy(qnetwork, env.nActions(), rng, 0.)
# --- Instantiate agent ---
agent = NeuralAgent(env,
qnetwork,
parameters.replay_memory_size,
max(env.inputDimensions()[i][0]
for i in range(len(env.inputDimensions()))),
parameters.batch_size,
rng,
train_policy=train_policy,
test_policy=test_policy)
# --- Bind controllers to the agent ---
# Before every training epoch (periodicity=1), we want to print a summary of the agent's epsilon, discount and
# learning rate as well as the training epoch number.
agent.attach(bc.VerboseController(evaluate_on='epoch', periodicity=1))
# During training epochs, we want to train the agent after every [parameters.update_frequency] action it takes.
# Plus, we also want to display after each training episode (!= than after every training) the average bellman
# residual and the average of the V values obtained during the last episode, hence the two last arguments.
agent.attach(
parameters.momentum,
parameters.clip_delta,
parameters.freeze_interval,
parameters.batch_size,
parameters.update_rule,
rng)
train_policy = EpsilonGreedyPolicy(qnetwork, env.nActions(), rng, 0.1)
test_policy = EpsilonGreedyPolicy(qnetwork, env.nActions(), rng, 0.)
# --- Instantiate agent ---
agent = NeuralAgent(
env,
qnetwork,
parameters.replay_memory_size,
max(env.inputDimensions()[i][0] for i in range(len(env.inputDimensions()))),
parameters.batch_size,
rng,
train_policy=train_policy,
test_policy=test_policy)
# --- Bind controllers to the agent ---
# Before every training epoch (periodicity=1), we want to print a summary of the agent's epsilon, discount and
# learning rate as well as the training epoch number.
agent.attach(bc.VerboseController(
evaluate_on='epoch',
periodicity=1))
# During training epochs, we want to train the agent after every [parameters.update_frequency] action it takes.
# Plus, we also want to display after each training episode (!= than after every training) the average bellman
# residual and the average of the V values obtained during the last episode, hence the two last arguments.