NePPO learns a player-independent potential function via a novel objective whose minimization yields an approximate Nash equilibrium for general-sum multi-agent games.
Tizero: Mastering multi-agent football with curriculum learning and self-play.arXiv preprint arXiv:2302.07515
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A modular RL framework separates basic gaits from task actions via an oscillator plus feedback and uses a posture state machine to switch between ball-seeking/kicking and fall recovery for bipedal soccer robots in simulation.
citing papers explorer
-
NePPO: Near-Potential Policy Optimization for General-Sum Multi-Agent Reinforcement Learning
NePPO learns a player-independent potential function via a novel objective whose minimization yields an approximate Nash equilibrium for general-sum multi-agent games.
-
Reinforcement Learning Enabled Adaptive Multi-Task Control for Bipedal Soccer Robots
A modular RL framework separates basic gaits from task actions via an oscillator plus feedback and uses a posture state machine to switch between ball-seeking/kicking and fall recovery for bipedal soccer robots in simulation.