
The paper proposes an Optimistic variant of the Proximal Policy Optimization (OPPO) algorithm that incorporates exploration in a principled manner, and proves that it achieves a √d²H³T-regret in episodic Markov decision processes with linear function approximation and adversarial rewards.


coremsg

provably-efficient-exploration-in-policy-optimization-for-markov-decision-processes-with-linear-function-approximation-and-adversarial-rewards


Provably Efficient Exploration in Policy Optimization for Markov Decision Processes with Linear Function Approximation and Adversarial Rewards
