[1906.05243] When to use parametric models in reinforcement learning?

We examine the question of when and how parametric models are most useful in reinforcement learning. In particular, we look at commonalities and differences between parametric models and experience replay. Replay-based learning algorithms share important traits with model-based approaches, including the ability to plan: to use more computation without additional data to improve predictions and behaviour. We discuss when to expect benefits from either approach, and interpret prior work in this context. We hypothesise that, under suitable conditions, replay-based algorithms should be competitive to or better than model-based algorithms if the model is used only to generate fictional transitions from observed states for an update rule that is otherwise model-free. We validated this hypothesis on Atari 2600 video games. The replay-based algorithm attained state-of-the-art data efficiency, improving over prior results with parametric models.

1 mentions: @helioRocha_
Date: 2019/06/13 02:18

Referring Tweets

@helioRocha_ "When to use parametric models in reinforcement learning?. (arXiv:1906.05243v1 [cs.LG])" #arXiv https://t.co/hoMsRqVrbx

Related Entries

Read more [DL輪読会]Deep Reinforcement Learning that Matters
Read more RL— Introduction to Deep Reinforcement Learning – Jonathan Hui – Medium
Read more CMU Neural Nets for NLP 2019 (11): Reinforcement Learning - YouTube
Read more [1908.01275] Deep Reinforcement Learning in System Optimization
Read more Multi-Armed Bandits, Conjugate Models and Bayesian Reinforcement Learning | Eigenfoo