OA-PI trains RL policies against the worst-case bounded action perturbation through a modified Bellman operator, and its TD3 and PPO variants improve robustness and nominal performance on Mujoco and Box2d tasks.
Certifiable robustness to adversarial state uncertainty in deep reinforcement learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Action Robust Reinforcement Learning via Optimal Adversary Aware Policy Optimization
OA-PI trains RL policies against the worst-case bounded action perturbation through a modified Bellman operator, and its TD3 and PPO variants improve robustness and nominal performance on Mujoco and Box2d tasks.