Introduction
CEMAgent
rl.agents.cem.CEMAgent(model, nb_actions, memory, batch_size=50, nb_steps_warmup=1000, train_interval=50, elite_frac=0.05, memory_interval=1, theta_init=None, noise_decay_const=0.0, noise_ampl=0.0)
Write me
References
- Learning Tetris Using the Noisy Cross-Entropy Method, Szita et al., 2006
- Deep Reinforcement Learning (MLSS lecture notes), Schulman, 2016