arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2104.07495cs.LGcs.AIstat.ML
收藏

通过潜在贝叶斯惊喜的好奇心驱动的探索

Curiosity-Driven Exploration via Latent Bayesian Surprise

Ghent University(根特大学)

Pietro Mazzaglia, Ozan Catal, Tim Verbelen, Bart Dhoedt

摘要:

人类追求知识的内在欲望,也被称为好奇心,被认为是获得技能的过程中必不可少的。在人工好奇心的帮助下,我们可以为当前的控制技术(如强化学习)配备更多的自然探索能力。在这方面,一个有前途的方法是对模型参数使用贝叶斯惊喜,即先验和后验信念之间差异的度量,以利于探索。在这方面的贡献,我们建议应用贝叶斯惊喜在一个潜在的空间代表代理的当前理解的系统的动态,大大降低了计算成本。我们广泛地评估我们的方法,通过测量代理的性能方面的环境探索,连续的任务,并期待在游戏中取得的成绩,视频游戏。我们的模型是计算成本低,积极与当前国家的最先进的方法在几个问题上比较。我们还研究了环境中的随机性所造成的影响,这通常是好奇心驱动的代理商的失败案例。在这种情况下,结果表明,我们的方法是弹性的随机过渡。

英文摘要:

The human intrinsic desire to pursue knowledge, also known as curiosity, is considered essential in the process of skill acquisition. With the aid of artificial curiosity, we could equip current techniques for control, such as Reinforcement Learning, with more natural exploration capabilities. A promising approach in this respect has consisted of using Bayesian surprise on model parameters, i.e. a metric for the difference between prior and posterior beliefs, to favour exploration. In this contribution, we propose to apply Bayesian surprise in a latent space representing the agent's current understanding of the dynamics of the system, drastically reducing the computational costs. We extensively evaluate our method by measuring the agent's performance in terms of environment exploration, for continuous tasks, and looking at the game scores achieved, for video games. Our model is computationally cheap and compares positively with current state-of-the-art methods on several problems. We also investigate the effects caused by stochasticity in the environment, which is often a failure case for curiosity-driven agents. In this regime, the results suggest that our approach is resilient to stochastic transitions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑