Bottom-up multi-agent reinforcement learning by reward shaping for cooperative-competitive tasks

Aotani, Takumi; Kobayashi, Taisuke; Sugimoto, Kenji

doi:10.1007/s10489-020-02034-2

Cited by 11 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The efficiency improvement over DQN is minimal, and the algorithm can only be applied in certain specific environments. Similar works have predicted the reward functions of other agents (bottom-up MARL) [38].…”

Section: Related Workmentioning

confidence: 64%

Modeling opponent learning in multiagent repeated games

Han

et al. 2022

Appl Intell

View full text Add to dashboard Cite

Multiagent reinforcement learning (MARL) has been used extensively in the game environment. One of the main challenges in MARL is that the environment of the agent system is dynamic, and the other agents are also updating their strategies. Therefore, modeling the opponents’ learning process and adopting specific strategies to shape learning is an effective way to obtain better training results. Previous studies such as DRON, LOLA and SOS approximated the opponent’s learning process and gave effective applications. However, these studies modeled only transient changes in opponent strategies and lacked stability in the improvement of equilibrium efficiency. In this article, we design the MOL (modeling opponent learning) method based on the Stackelberg game. We use best response theory to approximate the opponents’ preferences for different actions and explore stable equilibrium with higher rewards. We find that MOL achieves better results in several games with classical structures (the Prisoner’s Dilemma, Stackelberg Leader game and Stag Hunt with 3 players), and in randomly generated bimatrix games. MOL performs well in competitive games played against different opponents and converges to stable points that score above the Nash equilibrium in repeated game environments. The results may provide a reference for the definition of equilibrium in multiagent reinforcement learning systems, and contribute to the design of learning objectives in MARL to avoid local disadvantageous equilibrium and improve general efficiency.

show abstract

Section: Related Workmentioning

confidence: 64%

Modeling opponent learning in multiagent repeated games

Han

et al. 2022

Appl Intell

View full text Add to dashboard Cite

show abstract

“…To spot the differences between cooperative innovation projects and task conflict, the teacher plays a role in mediating how ambiguous and tacit knowledge is obtained from sharing open groups in a constructive debate approach based on local knowledge and experience (Mu et al, 2021). It can be integrated into competitive tasks (Aotani et al, 2021) and student-centered learning tipped to use authentic materials, attractive features, and .feedback (Yassin et al, 2019). Thus, the teacher's roles are to help students fully engage in learning activities and to avoid ambiguity and conflict when addressing learning materials.…”

Section: The Global-oriented Actionsmentioning

confidence: 99%

The Transformative Roles of Cooperative Learning in Promoting EFL Students' Writing Competence

Sudirman,

Fifardin,

Berkanis

2023

edu-ling

View full text Add to dashboard Cite

Cooperative learning is primarily aligned with the transformative roles that it can play in responding to EFL students' writing skills. This review article investigates the personal, relational, educational, institutional, and global aspects of cooperative learning transformatively. Personal efforts to improve writing skills highlight the relevance of diverse small-scale teamwork. Individual student efforts are the gold standard for adopting coordination and teamwork. More significantly, students want to regain self-confidence by adopting socio-emotional skills that improve their collaboration and involvement. It also maintains a positive attitude and a sense of pride in the face of institutional transformation. The main reason is that institutional policy, which heavily encourages writing competence, attempts to help students develop and update their knowledge, communication, creativity, responsibility, and competence capacities. As a result, transformative learning brings together the strengths of small-scale personal, relational, educational, and institutional activities to develop networked relationships in academic communities. Furthermore, cooperative learning functions well in writing contexts to assist students in accepting democratic ideals, attitudes, and principles. Cooperative learning thus plays transformative roles while enhancing students' writing competence in global contexts to re-articulate ideas that transformational values arise through in-class writing activities that contribute to global cooperative learning. Keywords: Cooperative learning, Transformative Role, Writing Competence, EFL writing

show abstract

Skill Reward for Safe Deep Reinforcement Learning

Cheng

Zhang

et al. 2022

Communications in Computer and Information Science

View full text Add to dashboard Cite

Bottom-up multi-agent reinforcement learning by reward shaping for cooperative-competitive tasks

Cited by 11 publications

References 20 publications

Modeling opponent learning in multiagent repeated games

Modeling opponent learning in multiagent repeated games

The Transformative Roles of Cooperative Learning in Promoting EFL Students' Writing Competence

Skill Reward for Safe Deep Reinforcement Learning

Contact Info

Product

Resources

About