Tag: adversarial reinforcement learning
Browse our exclusive articles!
M2GRPO: Multi-Agent Policy Optimization for Underwater Robots
Discover M2GRPO, a novel multi-agent policy optimization method enhancing biomimetic underwater robots' cooperative pursuit and decision-making.
LASER: Adaptive Active Sensing for Continuum Field Reconstruction
Discover LASER, a reinforcement learning framework that enhances continuum field reconstruction with adaptive active sensing and high-fidelity measurements...
Verbal Tics in Large Language Models: Systematic Study
Explore the rise of verbal tics in top LLMs, their impact on naturalness, and the need for improved alignment to enhance AI-human communication.
Adaptive Reinforcement Learning for Bipedal Soccer Robots
Discover how adaptive reinforcement learning improves multi-task control and stability in bipedal soccer robots for enhanced performance.
Multi-Gait Learning for Humanoids via Selective Adversarial RL
Discover how selective adversarial motion prior boosts multi-gait learning in humanoid robots using reinforcement learning and sim-to-real transfer.