The discount factor in reinforcement learning controls both the effective planning horizon and the strength of bootstrapping, yet most deep RL methods use a single fixed value across all states. While state-dependent discounting is conceptually appealing, naive deep actor--critic implementations can become unstable and degenerate toward TD-error collapse. We propose AdaGamma, a practical deep actor--critic method for state-dependent discounting that learns a state-dependent discount function together with a return-consistency objective to regularize the induced backup structure. On the theory side, we analyze the Bellman operator induced by state-dependent discounting and establish its basic well-posedness properties under suitable conditions. Empirically, AdaGamma integrates into both SAC and PPO, yielding consistent improvements on continuous-control benchmarks, and achieves statistically significant gains in an online A/B test on the JD Logistics platform. These results suggest that state-dependent discounting can be made effective in deep RL when coupled with a return-consistency objective that prevents degenerate target manipulation.
@article{arxiv.2605.06149,
title = {AdaGamma: State-Dependent Discounting for Temporal Adaptation in Reinforcement Learning},
author = {Yaomin Wang and Jianting Pan and Ran Tian and Xiaoyang Li and Yu Zhang and Hengle Qin and Tianshu YU},
journal= {arXiv preprint arXiv:2605.06149},
year = {2026}
}