Papers › Temporal Shift Reinforcement Learning

Temporal Shift Reinforcement Learning

5 Sep 2021arXiv:2109.02145archive 2025-07-28

Deepak George Thomas, Tichakorn Wongpiromsarn, Ali Jannesari

The function approximators employed by traditional image-based Deep Reinforcement Learning (DRL) algorithms usually lack a temporal learning component and instead focus on learning the spatial component. We propose a technique, Temporal Shift Reinforcement Learning (TSRL), wherein both temporal, as well as spatial components are jointly learned. Moreover, TSRL does not require additional parameters to perform temporal learning. We show that TSRL outperforms the commonly used frame stacking heuristic on both of the Atari environments we test on while beating the SOTA for one of them. This investigation has implications in the robotics as well as sequential decision-making domains.

Paper PDF Code

Code

Deepakgthomas/TSM_RL officialpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Decision Making Deep Reinforcement Learning Reinforcement Learning Reinforcement Learning (RL)Sequential Decision Making reinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Convolution DQN Dense Connections Q-Learning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections