Learning from Learners: Adapting Reinforcement Learning Agents to be Competitive in a Card Game

Barros, Pablo; Tanevska, Ana; Sciutti, Alessandra

doi:10.48550/arxiv.2004.04000

Cited by 6 publications

(14 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To simulate players in the game, we must train reinforcement learning agents. Following the original design proposed by the Chef's Hat authors [22], we will implement and train two types of agents: one based on Deep Q-Learning (DQL) and another one based on Proximal Policy Optimization (PPO). We need to implement these agents as their learned behavior will be our baseline for our final evaluation.…”

Section: Methodology and Experimental Protocolmentioning

confidence: 99%

“…DQL and PPO Playing Behavior on the Chef's Hat Card Game. In the same development wave, it was recently investigated the design and development of reinforcement learning agents to play the four players Chef's Hat competitive card game [22]. These agents were based on Deep Q-Learning (DQL) [23] and Proximal Policy Optimization (PPO) [24], and achieved success in learning how to win the game in different tasks: playing against random agents, self-play, and online adaptation towards the opponents.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Incorporating Rivalry in Reinforcement Learning for a Competitive Game

Barros¹,

Tanevska²,

Yalçın³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Recent advances in reinforcement learning with social agents have allowed us to achieve human-level performance on some interaction tasks. However, most interactive scenarios do not have as end-goal performance alone; instead, the social impact of these agents when interacting with humans is as important and, in most cases, never explored properly. This preregistration study focuses on providing a novel learning mechanism based on a rivalry social impact. Our scenario explored different reinforcement learning-based agents playing a competitive card game against human players. Based on the concept of competitive rivalry, our analysis aims to investigate if we can change the assessment of these agents from a human perspective.

show abstract

Section: Methodology and Experimental Protocolmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Incorporating Rivalry in Reinforcement Learning for a Competitive Game

Barros¹,

Tanevska²,

Yalçın³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…As discussed by Barros et al [20], the learning agents learn different strategies when trained to play the Chef's Hat game.…”

Section: The Learning Agentsmentioning

confidence: 99%

“…We deploy our experiments onto the multiplayer Chef's Hat card game [19] as it offers a dynamic interaction between the players and simulates directly the realworld counterpart game. In the scenarios' baseline, four agents play against each other and their performance is measured directly based on how many games they win [20]. It is not possible, however, without an extensive manual observation of their action-selection pattern to explain their winning behavior while the game happens.…”

Section: Introductionmentioning

confidence: 99%

Moody Learners -- Explaining Competitive Behaviour of Reinforcement Learning Agents

Barros¹,

Tanevska²,

Cruz³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Designing the decision-making processes of artificial agents that are involved in competitive interactions is a challenging task. In a competitive scenario, the agent does not only have a dynamic environment but also is directly affected by the opponents' actions. Observing the Q-values of the agent is usually a way of explaining its behavior, however, it does not show the temporal-relation between the selected actions. We address this problem by proposing the Moody framework that creates an intrinsic representation for each agent based on the Pleasure/Arousal model. We evaluate our model by performing a series of experiments using the competitive multiplayer Chef's Hat card game and discuss how by observing the intrinsic state generated by our model allows us to obtain a holistic representation of the competitive dynamics within the game.

show abstract

“…By exploring, a standard agent learns solely from the signals it receives from the environment. The RL approach has shown success in domains such as robotics [3,4], game-playing [5,6], and inventory management [7], among others.…”

Section: Introductionmentioning

confidence: 99%

A Conceptual Framework for Externally-influenced Agents: An Assisted Reinforcement Learning Review

Bignold,

Cruz,

Taylor

et al. 2020

Preprint

View full text Add to dashboard Cite

A long-term goal of reinforcement learning agents is to be able to perform tasks in complex real-world scenarios. The use of external information is one way of scaling agents to more complex problems. However, there is a general lack of collaboration or interoperability between different approaches using external information. In this work, we propose a conceptual framework and taxonomy for assisted reinforcement learning, aimed at fostering such collaboration by classifying and comparing various methods that use external information in the learning process. The proposed taxonomy details the relationship between the external information source and the learner agent, highlighting the process of information decomposition, structure, retention, and how it can be used to influence agent learning. As well as reviewing state-of-the-art methods, we identify current streams of reinforcement learning that use external information in order to improve the agent's performance and its decision-making process. These include heuristic reinforcement learning, interactive reinforcement learning, learning from demonstration, transfer learning, and learning from multiple sources, among others. These streams of reinforcement learning operate with the shared objective of scaffolding the learner agent. Lastly, we discuss further possibilities for future work in the field of assisted reinforcement learning systems.

show abstract

Learning from Learners: Adapting Reinforcement Learning Agents to be Competitive in a Card Game

Cited by 6 publications

References 0 publications

Incorporating Rivalry in Reinforcement Learning for a Competitive Game

Incorporating Rivalry in Reinforcement Learning for a Competitive Game

Moody Learners -- Explaining Competitive Behaviour of Reinforcement Learning Agents

A Conceptual Framework for Externally-influenced Agents: An Assisted Reinforcement Learning Review

Contact Info

Product

Resources

About