Filters








10 Hits in 4.4 sec

MARLeME: A Multi-Agent Reinforcement Learning Model Extraction Library [article]

Dmitry Kazhdan, Zohreh Shams, Pietro Liò
2020 arXiv   pre-print
Multi-Agent Reinforcement Learning (MARL) encompasses a powerful class of methodologies that have been applied in a wide range of fields.  ...  RoboCup Takeaway was proposed in [16] in order to facilitate RL research in the context of RoboCup Soccer 4 , and focuses on two teams of simulated agents playing the Takeaway game in a twodimensional  ...  Experiments We evaluate MARLeME on two well-known RL case studies: Mountain Car [23] and RoboCup Takeaway [16] , using AA-based agents as the extracted models.  ... 
arXiv:2004.07928v1 fatcat:hb25irjbyfcrdfjzlkb36f46ju

AN EMPIRICAL STUDY OF POTENTIAL-BASED REWARD SHAPING AND ADVICE IN COMPLEX, MULTI-AGENT SYSTEMS

SAM DEVLIN, DANIEL KUDENKO, MAREK GRZEŚ
2011 Advances in Complex Systems  
This paper investigates the impact of reward shaping in multi-agent reinforcement learning as a way to incorporate domain knowledge about good strategies.  ...  The results illustrate that reward shaping with multiple, simultaneous learning agents can reduce the time needed to learn a suitable policy and can alter the final group performance.  ...  The subsequent section introduces RoboCup Soccer, KeepAway and TakeAway; the chosen problem domains.  ... 
doi:10.1142/s0219525911002998 fatcat:nvs2v5jup5enxkc77yr4tzbqiy

A Survey of Opponent Modeling in Adversarial Domains

Samer Nashed, Shlomo Zilberstein
2022 The Journal of Artificial Intelligence Research  
We discuss all the components of opponent modeling systems, including feature extraction, learning algorithms, and strategy abstractions.  ...  These discussions lead us to propose a new form of analysis for describing and predicting the evolution of game states over time.  ...  We also thank the editors for their patience and guidance.  ... 
doi:10.1613/jair.1.12889 fatcat:o6wlyjr2gvdz3fs6b6szr6y55u

State Elimination in Accelerated Multiagent Reinforcement Learning

Ary Setijadi Prihatmanto, Widyawardana Adiprawita, Safreni Candra Sari, Kuspriyanto Kuspriyanto
2016 International Journal on Electrical Engineering and Informatics  
This paper presents a novel algorithm of Multiagent Reinforcement Learning called State Elimination in Accelerated Multiagent Reinforcement Learning (SEA-MRL), that successfully produces faster learning  ...  This algorithm is generally applicable for other multiagent task challenges or general multiagent learning with large scale state space, and perfectly applicable with no adjustments for single agent learning  ...  Gao and Toni [19] incorporate heuristic, represented by arguments in value-based argumentation into RL by using Heuristically Accelerated RL techniques in RoboCup Soccer Keepaway-Takeaway game.  ... 
doi:10.15676/ijeei.2016.8.3.12 fatcat:aydhzofht5hfhlypek4xkterpq

Online State Elimination in Accelerated reinforcement Learning

Safreni Candra Sari, Kuspriyanto Kuspriyanto, Ary Setijadi Prihatmanto, Widyawardana Adiprawita
2014 International Journal on Electrical Engineering and Informatics  
In this paper a novel algorithm called Online State Elimination in Accelerated Reinforcement Learning (OSE-ARL) is introduced.  ...  This algorithm is generally applicable for other robotic task challenges or general robotics learning with large scale state space.  ...  [19] incorporate heuristic, represented by arguments in value-based argumentation into RL by using Heuristically Accelerated RL techniques in RoboCup Soccer Keepaway-Takeaway game.  ... 
doi:10.15676/ijeei.2014.6.4.3 fatcat:x7b7lqcl7favbloav44qlafqvi

Shifting Perspectives on AI Evaluation: The Increasing Role of Ethics in Cooperation

Enrico Barbierato, Maria Enrica Zamponi
2022 AI  
a more suitable benchmark for AI applications.  ...  An evaluation based uniquely on the capacity of playing games, even when enriched by the capability of learning complex rules without any human supervision, is bound to be unsatisfactory.  ...  Finally, cooperative learning has proven to be successful in educational areas (especially with children) and has been adopted in machine learning, applying algorithms based on reinforcement learning.  ... 
doi:10.3390/ai3020021 fatcat:lt2tmnx5anek5bmj7yz6ht5niy

MARLeME: A Multi-Agent Reinforcement Learning Model Extraction Library [article]

Zohreh Shams, Kazhdan Dmitry, Liò Pietro, Apollo-University Of Cambridge Repository
2020
Multi-Agent Reinforcement Learning (MARL) en-compasses a powerful class of methodologies that have beenapplied in a wide range of fields.  ...  ), using extracted models based on AbstractArgumentation.  ...  RoboCup Takeaway was proposed in [15] in order to facilitate RL research in the context of RoboCup Soccer 2 , and focuses on two teams of simulated agents playing the Takeaway game in a two-dimensional  ... 
doi:10.17863/cam.58355 fatcat:wjdjvkpqzrapvbsssxd2z3m47a

Leveling the Playing Field – Fairness in AI Versus Human Game Benchmarks [article]

Rodrigo Canaan, Christoph Salge, Julian Togelius, Andy Nealen
2019 arXiv   pre-print
Only relatively recently has this target been finally met for traditional tabletop games such as Backgammon, Chess and Go.  ...  Another category that could be considered is that of games involving direct interaction with the real world, such as the aforementioned Robocup [46] , where robots play soccer against robots.  ...  learning environment for the game in 2017 [53] .  ... 
arXiv:1903.07008v4 fatcat:wbwtsjvaffgu7er7btsvpzzwse

Using Argumentation to Improve Classification in Natural Language Problems

Lucas Carstens, Francesca Toni
2017 ACM Transactions on Internet Technology  
On the other hand we address a form of argumentation mining that we call Relation-based Argumentation Mining, where we classify pairs of sentences based on whether the first sentence attacks or supports  ...  Over the past decade or so advances in this field have commonly relied on data-driven solutions, i.e. machine learning.  ...  AARL employs Value-Based Argumentation [16] to improve the learning of agents' strategies in the Multi-Agent game of RoboCup Keepaway-Takeaway (KATA).  ... 
doi:10.1145/3017679 fatcat:dt5n5efxkfcvlkdbxnmnngs5g4

Transferable strategic meta-reasoning models

Michael Wunder
2013
depth of reasoning over base rules and time-horizon of planning.  ...  For the first time, a confluence of advances in agent design, formation of massive online data sets of social behavior, and computational techniques have allowed for researchers to construct and learn  ...  In the first one, cooperation or coordination of a population of decentralized agents is required to achieve some high-level goal, like a team of robotic soccer players in the Robocup tournament.  ... 
doi:10.7282/t3jh3j8k fatcat:jrwgrekgknal3dh6gnkkdibsdi