conftrace_

reward safety trade-off

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

soft switching (1) reward safety optimization (1) policy adjustment (1) gradient manipulation (1) safe reinforcement learning (1) convergence analysis (1) policy optimization (1)

Papers

Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation AAAI 2024