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

### Like this:

Like Loading...