SafeExplorer: An Unbiased Mixed-Policy Gradient for Reinforcement Learning with Recovery Interventions
SafeExplorer addresses safety risks when training robots by using a mixed policy where an agent switches to a recovery policy outside a safe zone. It proposes an unbiased policy gradient estimator that ignores the recovery policy's density, ensuring reliable learning even with deterministic recoveries. This method significantly reduces training falls while maintaining or exceeding standard PPO performance.