IEEE

CVaR-Constrained Policy Optimization for Safe Reinforcement Learning

Abstract: Current constrained reinforcement learning (RL) methods guarantee constraint satisfaction only in expectation, which is inadequate for safety-critical decision problems. Since a constraint ...
IEEE

SA-MARL: Novel Self-Attention-Based Multi-Agent Reinforcement Learning With Stochastic ...

Abstract: In the rapidly advancing Reinforcement Learning (RL) field, Multi-Agent Reinforcement Learning (MARL) has emerged as a key player in solving complex real-world challenges. A pivotal ...