Value-based CTDE Methods in Symmetric Two-team Markov Game: from Cooperation to Team Competition
2. prosince 2022
Řečníci
Pascal Leroy
Speaker · 0 followers
Jonathan Pisane
Speaker · 0 followers
Damien Ernst
Speaker · 0 followers
O prezentaci
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…
Organizátor
NeurIPS 2022
Account · 962 followers
Baví vás formát? Nechte SlidesLive zachytit svou akci!
Profesionální natáčení a streamování po celém světě.
Sdílení
Doporučená videa
Prezentace na podobné téma, kategorii nebo přednášejícího
Where do models go wrong? Parameter-space saliency maps for explainability
Watch later
Roman Levin, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
What Art can tell us about the brain.
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Learning neural causal models
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Imbalance Trouble: Revisiting Neural-Collapse Geometry
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Prompt Certified Machine Unlearning with Randomized Gradient Smoothing and Quantization
Watch later
Zijie Zhang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
General policy mapping: online continual reinforcement learning inspired on the insect brain
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%