AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

Off-Policy Reinforcement Learning with Delayed Rewards

Beining Han, Zhizhou Ren, Zuofan Wu, Yuan Zhou, Jian Peng

ICML 2022 · Reinforcement learning › Policy gradient and actor-critic · approach: Regularized scalable deep value learning · 14 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Replace the original Q-function with the trajectory-based Q-function and its corresponding policy updateOff-policy RL for delayed-reward PI-DRMDPs · Toy PI-DRMDP-0expected discounted return: -0.495γ -> 0Improved
Use the proposed Q-function framework instead of vanilla SACContinuous-control PI-DRMDP tasks · OpenAI Gym delayed-reward taskstraining performanceImproved
Use HC decomposition instead of a recurrent network to approximate the proposed Q-function (ablation)Proposed off-policy algorithm · High-dimensional delayed-reward taskssample efficiency and stabilityImproved
Use Pairwise-1 history representation (ablation)HC-decomposed proposed algorithm · Continuous-control PI-DRMDP taskstraining performanceImproved
Remove regularization on the history component (ablation)HC-decomposed proposed algorithm · Continuous-control delayed-reward taskstraining performanceHurt
Use HC-RNN instead of HC-Pairwise-1 (ablation)HC-decomposed proposed algorithm · Continuous-control PI-DRMDP taskstraining performanceMixed
Use HC-Singleton history representation (ablation)HC-decomposed proposed algorithm · Non-sum-form target-reaching tasksteps needed to reach the targetImproved
Replace SAC-based implementation with a TD3-based implementation (ablation)Proposed delayed-reward algorithm · Continuous-control delayed-reward taskstraining performanceHurt
Use SAC-IRCR smoothing guidanceOff-policy delayed-reward RL · Hopper-v2, Ant-v2, Walker2d-v2, and Reacher-v2training performanceMixed
Use HC decomposition instead of Q-RNN (ablation)Proposed off-policy algorithm · Non-sum-form delayed-reward taskstraining performanceImproved
Use LIRPG or RUDDER instead of the proposed algorithmDelayed-reward RL · High-dimensional delayed-reward taskstraining performanceHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy