1. the complete title of one (or more) paper(s) published in the open literature describing the work that the author claims describes a human-competitive result;

Nondominated Policy-Guided Learning in Multi-Objective Reinforcement Learning

2. the name, complete physical mailing address, e-mail address, and phone number of EACH author of EACH paper(s);

Man-Je Kim; EECS Building A #515, Gwangju Institute of Science and Technology, Bukgu 123 Cheomdangwagiro, South Korea; jaykim0104@gist.ac.kr; +82-627153169
Hyunsoo Park; NCSOFT, Seongnam-si 13494, South Korea; 
hspark8312@ncsoft.com; +82-1091667222
Chang Wook Ahn; EECS Building A #502, Gwangju Institute of Science and Technology, Bukgu 123 Cheomdangwagiro, South Korea; cwan@gist.ac.kr;+82-627152264

3. the name of the corresponding author (i.e., the author to whom notices will be sent concerning the competition);

Chang Wook Ahn

4. the abstract of the paper(s);

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. Multiobjective 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.

5. a list containing one or more of the eight letters (A, B, C, D, E, F, G, or H) that correspond to the criteria (see above) that the author claims that the work satisfies;

(B)

6. a statement stating why the result satisfies the criteria that the contestant claims (see examples of statements of human-competitiveness as a guide to aid in constructing this part of the submission);

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 fits 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 in finding various pareto optimals of multi-objectives due to the greedy nature of reinforcement learning. This paper aims to improve diversity for Mo-V MPO, which has been used previously to solve multi-obejctive reinforcement learning. In this paper, we proposed a policy assimilation based on non-dominated sort, which is often used for multi-objective optimization in evolutionary computation.

7. a full citation of the paper (that is, author names; title, publication date; name of journal, conference, or book in which article appeared; name of editors, if applicable, of the journal or edited book; publisher name; publisher city; page numbers, if applicable);

Kim M-J, Park H, Ahn CW. Nondominated Policy-Guided Learning in Multi-Objective Reinforcement Learning. Electronics. 2022; 11(7):1069. https://doi.org/10.3390/electronics11071069

8. a statement either that "any prize money, if any, is to be divided equally among the co-authors" OR a specific percentage breakdown as to how the prize money, if any, is to be divided among the co-authors;

Any prize money, if any, is to be divided equally among the co-authors.

9. a statement stating why the authors expect that their entry would be the "best," and

Reinforcement learning is a core technology of intelligence control, but its exploitation is often hindered by many difficulties in multi-objective optimization. The method we have proposed is a high-valued multi-objective optimization reinforcement learning technique in a simple structure that guarantees a competent level of generalization and applicability. In a point of view that it can be provided as one of the important foundations for intelligence control based on multi-objective reinforcement learning that just began its era, we claim that our study has proven itself sufficiently capable to participate in this competition.

10. An indication of the general type of genetic or evolutionary computation used, such as GA (genetic algorithms), GP (genetic programming), ES (evolution strategies), EP (evolutionary programming), LCS (learning classifier systems), GI (genetic improvement), GE (grammatical evolution), GEP (gene expression programming), DE (differential evolution), etc.

ES

11. The date of publication of each paper.  If the date of publication is not on or before the deadline for submission, but instead, the paper has been unconditionally accepted for publication and is “in press” by the deadline for this competition, the entry must include a copy of the documentation establishing that the paper meets the "in press" requirement.

In Press