Tag: adversarial reinforcement learning
Browse our exclusive articles!
Delayed Homomorphic RL: Efficient Learning with Feedback Delay
Discover Delayed Homomorphic Reinforcement Learning (DHRL) for handling delayed feedback, reducing sample complexity, and improving RL performance in dynam...
Multi-Robot Task Allocation Using Actor-Critic Learning
Optimize multi-robot multi-queue control with exhaustive assignment actor-critic learning for efficient task allocation in asymmetric environments.
Optimizing Neurorobot Learning with Limited Demo Data
Enhance neurorobot policies using preference regret to learn effectively from limited demonstration data and improve robotic control performance.
Sim2Real-AD: Deploy VLM-Guided RL in Real Autonomous Driving
Sim2Real-AD enables zero-shot deployment of VLM-guided reinforcement learning from simulation to real autonomous vehicles with high success rates.
QED-Nano: Small AI Model Excels in Hard Math Proofs
Discover QED-Nano, a compact AI model achieving top-tier performance in complex mathematical proofs with open training and low inference cost.