Importance of using appropriate baselines for evaluation of data-efficiency in deep reinforcement learning for Atari

no code implementations • 23 Mar 2020 • Kacper Kielak

Namely, we show that the actual improvement in the efficiency came from allowing the algorithm for more training updates for each data sample, and not from employing the new methods.

reinforcement-learning Reinforcement Learning (RL)

Generative Adversarial Imagination for Sample Efficient Deep Reinforcement Learning

no code implementations • 30 Apr 2019 • Kacper Kielak

Reinforcement learning has seen great advancements in the past five years.

Game of Go reinforcement-learning +1