Timezone: »

Off-Policy Reinforcement Learning with Delayed Rewards
Beining Han · Zhizhou Ren · Zuofan Wu · Yuan Zhou · Jian Peng

Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #927

We study deep reinforcement learning (RL) algorithms with delayed rewards. In many real-world tasks, instant rewards are often not readily accessible or even defined immediately after the agent performs actions. In this work, we first formally define the environment with delayed rewards and discuss the challenges raised due to the non-Markovian nature of such environments. Then, we introduce a general off-policy RL framework with a new Q-function formulation that can handle the delayed rewards with theoretical convergence guarantees. For practical tasks with high dimensional state spaces, we further introduce the HC-decomposition rule of the Q-function in our framework which naturally leads to an approximation scheme that helps boost the training efficiency and stability. We finally conduct extensive experiments to demonstrate the superior performance of our algorithms over the existing work and their variants.

Author Information

Beining Han (IIIS, Tsinghua)
Zhizhou Ren (University of Illinois at Urbana-Champaign)
Zuofan Wu (Helixon Research)
Yuan Zhou (UIUC)
Jian Peng (UIUC)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors