Value-based CTDE Methods in Symmetric Two-team Markov Game: from Cooperation to Team Competition
Dec 2, 2022
Speakers
Pascal Leroy
Speaker · 0 followers
Jonathan Pisane
Speaker · 0 followers
Damien Ernst
Speaker · 0 followers
About
In this paper, we identify the best training scenario to train a team of agents to compete against multiple possible strategies of opposing teams.We restrict ourselves to the case of a symmetric two-team Markov game which is a competition between two symmetric teams.We evaluate cooperative value-based methods in a mixed cooperative-competitive environment.We selected three training methods based on the centralised training and decentralised execution (CTDE) paradigm: QMIX, MAVEN and QVMix.To train such teams, we modified the StarCraft Multi-Agent Challenge environment to create competitive scenarios where both teams could learn and compete simultaneously in a partially observable environment.For each method, we considered three learning scenarios differentiated by the variety of team policies encountered during training.Our results suggest that training against multiple evolving strategies achieves the best results when, for scoring their performances, teams are faced with several strategies, whether the stationary strategy is better than all trained teams or not.In this paper, we identify the best training scenario to train a team of agents to compete against multiple possible strategies of opposing teams.We restrict ourselves to the case of a symmetric two-team Markov game which is a competition between two symmetric teams.We evaluate cooperative value-based methods in a mixed cooperative-competitive environment.We selected three training methods based on the centralised training and decentralised execution (CTDE) paradigm: QMIX, MAVEN and QVMix.To tra…
Organizer
NeurIPS 2022
Account · 962 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Rethinking Sharpness-Aware Minimization as Variational Inference
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
NAS-Bench-Suite-Zero: Accelerating Research on Zero Cost Proxies
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Contrastive Neural Ratio Estimation
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
So ManyFolds, So Little Time: Efficient Protein Structure Prediction With pLMs and MSAs
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Safety Guarantees for Neural Network Dynamic Systems via Stochastic Barrier Functions
Watch later
Rayan Mazouz, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Dual-Curriculum Contrastive Multi-Instance Learning for Cancer Prognosis Analysis with Whole Slide Images
Watch later
Chao Tu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%