Author

E. Daneshmand

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

SafeExplorer: An Unbiased Policy Gradient for Reinforcement Learning with Recovery Interventions

The resulting algorithm reduces training-time falls by factors of 233x, 48x, and 26x on HalfCheetah, Ant, and Unitree Go1 over standard PPO, while matching or exceeding PPO's final reward, and on Ant, where the recovery policy is unreliable, it is the only method that reaches 80% of the best final reward.

E. Daneshmand, Majid Khadiv, Glen Berseth et al. · arXiv.org · 0 citations