VAST: Value Function Factorization with Variable Agent Sub-Teams
Dec 6, 2021
Speakers
Thomy Phan
Speaker · 0 followers
Fabian Ritz
Speaker · 0 followers
Lenz Belzner
Speaker · 0 followers
Philipp Altmann
Speaker · 0 followers
Thomas Gabor
Speaker · 0 followers
Claudia Linnhoff-Popien
Speaker · 0 followers
About
Value function factorization (VFF) is a popular approach to cooperative multi-agent reinforcement learning in order to learn local value functions from global rewards. However, state-of-the-art VFF is limited to a handful of agents in most domains. We hypothesize that this is due to the flat factorization scheme, where the VFF operator becomes a performance bottleneck with an increasing number of agents. Therefore, we propose VFF with variable agent sub-teams (VAST). VAST approximates a factorization for sub-teams which can be defined in an arbitrary way and vary over time, e.g., to adapt to different situations. The sub-team values are then linearly decomposed for all sub-team members. Thus, VAST can learn on a more focused and compact input representation of the original VFF operator. We evaluate VAST in three multi-agent domains and show that VAST can significantly outperform state-of-the-art VFF, when the number of agents is sufficiently large.Value function factorization (VFF) is a popular approach to cooperative multi-agent reinforcement learning in order to learn local value functions from global rewards. However, state-of-the-art VFF is limited to a handful of agents in most domains. We hypothesize that this is due to the flat factorization scheme, where the VFF operator becomes a performance bottleneck with an increasing number of agents. Therefore, we propose VFF with variable agent sub-teams (VAST). VAST approximates a factoriz…
Organizer
NeurIPS 2021
Account · 1.9k followers
About NeurIPS 2021
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
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
Adaptively Calibrated Critic Estimates for Deep Reinforcement Learning
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Fast Abductive Learning by Similarity-based Consistency Optimization
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Fast Certified Robust Training with Short Warmup
Watch later
Zhouxing Shi, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Data-Driven Offline Optimization for Architecting Hardware Accelerators
Watch later
Aviral Kumar, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Maximum Mean Discrepancy for Generalization in the Presence of Distribution and Missingness Shift
Watch later
Liwen Ouyang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Oral Session 1: Generative Modeling
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%