Loading...
Please wait, while we are loading the content...
Similar Documents
Model-Based Multi-Objective Reinforcement Learning by a Reward Occurrence Probability Vector
| Content Provider | Semantic Scholar |
|---|---|
| Author | Yamaguchi, Tomohiro Nagahama, Shota Ichikawa, Yoshihiro Honma, Yoshimichi Takadama, K. |
| Copyright Year | 2020 |
| Abstract | This chapter describes solving multi-objective reinforcement learning (MORL) problems where there are multiple conflicting objectives with unknown weights. Previous model-free MORL methods take large number of calculations to collect a Pareto optimal set for each V/Q-value vector. In contrast, model-based MORL can reduce such a calculation cost than model-free MORLs. However, previous modelbased MORL method is for only deterministic environments. To solve them, this chapter proposes a novel model-based MORL method by a reward occurrence probability (ROP) vector with unknown weights. The experimental results are reported under Model-Based Multi-Objective Reinforcement Learning by a Reward Occurrence Probability Vector |
| Starting Page | 269 |
| Ending Page | 295 |
| Page Count | 27 |
| File Format | PDF HTM / HTML |
| DOI | 10.4018/978-1-7998-1382-8.ch010 |
| Alternate Webpage(s) | https://www.igi-global.com/viewtitlesample.aspx?id=244818&ptid=232677&t=model-based+multi-objective+reinforcement+learning+by+a+reward+occurrence+probability+vector |
| Alternate Webpage(s) | https://doi.org/10.4018/978-1-7998-1382-8.ch010 |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
