cartpole

https://github.com/matthiasplappert/keras-rl/blob/master/examples/cem_cartpole.py

increased nb_steps_wamup and nb_steps and chance of stablization is high

cem = CEMAgent(model=model, nb_actions=nb_actions, memory=memory,
               batch_size=500, nb_steps_warmup=50000, train_interval=50, elite_frac=0.05)
cem.compile()

cem.fit(env, nb_steps=500000, visualize=False, verbose=1)

failed to find success parameters / models for dqn agent

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s