# Horizon Reduction as Information Loss in Offline Reinforcement Learning

arXiv: https://arxiv.org/abs/2601.00831 · HTML: https://mlsanity.com/paper/2601.00831/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Offline RL algorithms, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 10 of its 17 references that are in the map.
- First posted on arXiv 25 Dec 2025.

## Placed in

- Offline RL and imitation learning from data / [Offline RL algorithms](https://mlsanity.com/offlinerl/offline-rl-algorithms/)

## Builds on (most cited first, 10 of 10)

- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://mlsanity.com/paper/2005.01643/) (2020)
- [Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2006.04779/) (2020)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [Off-Policy Deep Reinforcement Learning without Exploration](https://mlsanity.com/paper/1812.02900/) (2018)
- [Offline Reinforcement Learning as One Big Sequence Modeling Problem](https://mlsanity.com/paper/2106.02039/) (2021)
- [Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism](https://mlsanity.com/paper/2103.12021/) (2021)
- [A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problems](https://mlsanity.com/paper/2203.01387/) (2022)
- [Learning Markov State Abstractions for Deep Reinforcement Learning](https://mlsanity.com/paper/2106.04379/) (2021)
- [An Information-Theoretic Perspective on Credit Assignment in Reinforcement Learning](https://mlsanity.com/paper/2103.06224/) (2021)
- [Averaging n-step Returns Reduces Variance in Reinforcement Learning](https://mlsanity.com/paper/2402.03903/) (2024)

## Abstract (arXiv)

Horizon reduction is a common design strategy in offline reinforcement learning (RL), used to mitigate long-horizon credit assignment, improve stability, and enable scalable learning through truncated rollouts, windowed training, or hierarchical decomposition (Levine et al., 2020; Prudencio et al., 2023; Park et al., 2025). Despite recent empirical evidence that horizon reduction can improve scaling on challenging offline RL benchmarks, its theoretical implications remain underdeveloped (Park et al., 2025). In this paper, we show that horizon reduction can induce fundamental and irrecoverable information loss in offline RL. We formalize horizon reduction as learning from fixed-length trajectory segments and prove that, under this paradigm and any learning interface restricted to fixed-length trajectory segments, optimal policies may be statistically indistinguishable from suboptimal ones even with infinite data and perfect function approximation. Through a set of minimal counterexample Markov decision processes (MDPs), we identify three distinct structural failure modes: (i) prefix indistinguishability leading to identifiability failure, (ii) objective misspecification induced by truncated returns, and (iii) offline dataset support and representation aliasing. Our results establish necessary conditions under which horizon reduction can be safe and highlight intrinsic limitations that cannot be overcome by algorithmic improvements alone, complementing algorithmic work on conservative objectives and distribution shift that addresses a different axis of offline RL difficulty (Fujimoto et al., 2019; Kumar et al., 2020; Gulcehre et al., 2020).