Loading...
Please wait, while we are loading the content...
Similar Documents
Nondominated Policy-Guided Learning in Multi-Objective Reinforcement Learning
| Content Provider | MDPI |
|---|---|
| Author | Kim, Man-Je Park, Hyunsoo Ahn, Chang Wook |
| Copyright Year | 2022 |
| Description | Control intelligence is a typical field where there is a trade-off between target objectives, and researchers in this field have longed for artificial intelligence that achieves the target objectives. Multi-objective deep reinforcement learning was sufficient to satisfy this need. In particular, multi-objective deep reinforcement learning methods based on policy optimization are leading the optimization of control intelligence. However, multi-objective reinforcement learning has difficulties when finding various Pareto optimals of multi-objectives due to the greedy nature of reinforcement learning. We propose a method of policy assimilation to solve this problem. This method was applied to MO-V-MPO, one of preference-based multi-objective reinforcement learning, to increase diversity. The performance of this method has been verified through experiments in a continuous control environment. |
| Starting Page | 1069 |
| e-ISSN | 20799292 |
| DOI | 10.3390/electronics11071069 |
| Journal | Electronics |
| Issue Number | 7 |
| Volume Number | 11 |
| Language | English |
| Publisher | MDPI |
| Publisher Date | 2022-03-28 |
| Access Restriction | Open |
| Subject Keyword | Electronics Reinforcement Learning Multi-objective Optimization Real-time Environment |
| Content Type | Text |
| Resource Type | Article |
