تقرير
#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning
العنوان: | #Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning |
---|---|
المؤلفون: | Tang, Haoran, Houthooft, Rein, Foote, Davis, Stooke, Adam, Chen, Xi, Duan, Yan, Schulman, John, De Turck, Filip, Abbeel, Pieter |
سنة النشر: | 2016 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Artificial Intelligence, Computer Science - Learning |
الوصف: | Count-based exploration algorithms are known to perform near-optimally when used in conjunction with tabular reinforcement learning (RL) methods for solving small discrete Markov decision processes (MDPs). It is generally thought that count-based methods cannot be applied in high-dimensional state spaces, since most states will only occur once. Recent deep RL exploration strategies are able to deal with high-dimensional continuous state spaces through complex heuristics, often relying on optimism in the face of uncertainty or intrinsic motivation. In this work, we describe a surprising finding: a simple generalization of the classic count-based approach can reach near state-of-the-art performance on various high-dimensional and/or continuous deep RL benchmarks. States are mapped to hash codes, which allows to count their occurrences with a hash table. These counts are then used to compute a reward bonus according to the classic count-based exploration theory. We find that simple hash functions can achieve surprisingly good results on many challenging tasks. Furthermore, we show that a domain-dependent learned hash code may further improve these results. Detailed analysis reveals important aspects of a good hash function: 1) having appropriate granularity and 2) encoding information relevant to solving the MDP. This exploration strategy achieves near state-of-the-art performance on both continuous control tasks and Atari 2600 games, hence providing a simple yet powerful baseline for solving MDPs that require considerable exploration. Comment: 10 pages main text + 10 pages supplementary. Published at NIPS 2017 |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/1611.04717 |
رقم الأكسشن: | edsarx.1611.04717 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |