David Mguni
5 papers · 2020–2023 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π§ Keyword Pioneer π Conference Polyglot (4) π Cross-Pollinator (13) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (12)
π£
Hot Topic Early Bird
Conferences
NIPS (2)
AAAI (1)
ICML (1)
IJCAI (1)
Top co-authors
Keywords
reinforcement learning
(2)
policy learning
(2)
multi-agent reinforcement learning
(2)
language modeling
(1)
convergence analysis
(1)
nash equilibrium
(1)
variance reduction
(1)
optimal baseline
(1)
determinantal point process
(1)
gradient estimator
(1)
cooperative learning
(1)
game ai
(1)
markov game
(1)
sparse reward
(1)
reward shaping
(1)
behavioral diversity
(1)
fictitious play
(1)
value function decomposition
(1)
switching control
(1)
cooperative task
(1)
Papers
ChessGPT: Bridging Policy Learning and Language Modeling
NIPS 2023
Learning to Shape Rewards Using a Game of Two Partners
AAAI 2023
On the Convergence of Fictitious Play: A Decomposition Approach
IJCAI 2022
Settling the Variance of Multi-Agent Policy Gradients
NIPS 2021
Multi-Agent Determinantal Q-Learning
ICML 2020