# Flattening Hierarchies with Policy Bootstrapping

arXiv: https://arxiv.org/abs/2505.14975 · HTML: https://mlsanity.com/paper/2505.14975/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Self-rewarding alignment and self-training, one of 13 directions in Synthetic data and self-improvement for LLMs.
- Builds on 50 of its 66 references that are in the map.
- First posted on arXiv 20 May 2025.

## Placed in

- Synthetic data and self-improvement for LLMs / [Self-rewarding alignment and self-training](https://mlsanity.com/synth/self-rewarding-alignment-and-self-training/)
- Deep reinforcement learning methods / [Deep RL algorithms and representations](https://mlsanity.com/deeprl/deep-rl-algorithms-and-representations/)

## Builds on (most cited first, 30 of 50)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://mlsanity.com/paper/2005.01643/) (2020)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [Offline Reinforcement Learning with Implicit Q-Learning](https://mlsanity.com/paper/2110.06169/) (2021)
- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [A Minimalist Approach to Offline Reinforcement Learning](https://mlsanity.com/paper/2106.06860/) (2021)
- [IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures](https://mlsanity.com/paper/1802.01561/) (2018)
- [Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning](https://mlsanity.com/paper/1910.00177/) (2019)
- [R3M: A Universal Visual Representation for Robot Manipulation](https://mlsanity.com/paper/2203.12601/) (2022)
- [Minimax Regret Bounds for Reinforcement Learning](https://mlsanity.com/paper/1703.05449/) (2017)
- [Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review](https://mlsanity.com/paper/1805.00909/) (2018)
- [Data-Efficient Hierarchical Reinforcement Learning](https://mlsanity.com/paper/1805.08296/) (2018)
- [The Option-Critic Architecture](https://mlsanity.com/paper/1609.05140/) (2016)
- [VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training](https://mlsanity.com/paper/2210.00030/) (2022)
- [Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning](https://mlsanity.com/paper/1910.11956/) (2019)
- [FeUdal Networks for Hierarchical Reinforcement Learning](https://mlsanity.com/paper/1703.01161/) (2017)
- [Maximum a Posteriori Policy Optimisation](https://mlsanity.com/paper/1806.06920/) (2018)
- [Contrastive Learning as Goal-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2206.07568/) (2022)
- [OGBench: Benchmarking Offline Goal-Conditioned RL](https://mlsanity.com/paper/2410.20092/) (2024)
- [Search on the Replay Buffer: Bridging Planning and Reinforcement Learning](https://mlsanity.com/paper/1906.05253/) (2019)
- [Equivalence Between Policy Gradients and Soft Q-Learning](https://mlsanity.com/paper/1704.06440/) (2017)
- [HIQL: Offline Goal-Conditioned RL with Latent States as Actions](https://mlsanity.com/paper/2307.11949/) (2023)
- [Goal-Conditioned Reinforcement Learning with Imagined Subgoals](https://mlsanity.com/paper/2107.00541/) (2021)
- [Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning](https://mlsanity.com/paper/2304.01203/) (2023)
- [Reinforcement Learning with Action-Free Pre-Training from Videos](https://mlsanity.com/paper/2203.13880/) (2022)
- [Deep Hierarchical Planning from Pixels](https://mlsanity.com/paper/2206.04114/) (2022)
- [Foundation Policies with Hilbert Representations](https://mlsanity.com/paper/2402.15567/) (2024)

## Built on by (most cited first, 11 of 11)

- [Test-time Offline Reinforcement Learning on Goal-related Experience](https://mlsanity.com/paper/2507.18809/) (2025)
- [Test-Time Graph Search for Goal-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2510.07257/) (2025)
- [NFTR: From Provable Mode-Averaging to Geodesic Subgoal Selection in Offline Goal-Conditioned RL](https://mlsanity.com/paper/2607.07855/) (2026)
- [Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2604.20627/) (2026)
- [Beyond Success Rates: Trainability and Extractability for Offline GCRL](https://mlsanity.com/paper/2602.05459/) (2026)
- [QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL](https://mlsanity.com/paper/2605.01862/) (2026)
- [DAGR: State-Conditioned Goal Representations via Difference-Aware Goal Cross-Attention](https://mlsanity.com/paper/2607.13731/) (2026)
- [Locally-Guided Actor-Critic: Training a Goal-conditioned Actor with a Subgoal-aware Critic](https://mlsanity.com/paper/2608.30406/) (2026)
- [Learning Goal-Reaching Quasimetric Geometry From Finite-Time Reachability](https://mlsanity.com/paper/2610.00778/) (2026)
- [Direction-Conditioned Policies for Online Goal-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2610.05087/) (2026)
- [Hyperspherical Contrastive Representations Unlock Planning and Exploration](https://mlsanity.com/paper/2610.20409/) (2026)

## Abstract (arXiv)

Offline goal-conditioned reinforcement learning (GCRL) is a promising approach for pretraining generalist policies on large datasets of reward-free trajectories, akin to the self-supervised objectives used to train foundation models for computer vision and natural language processing. However, scaling GCRL to longer horizons remains challenging due to the combination of sparse rewards and discounting, which obscures the comparative advantages of primitive actions with respect to distant goals. Hierarchical RL methods achieve strong empirical results on long-horizon goal-reaching tasks, but their reliance on modular, timescale-specific policies and subgoal generation introduces significant additional complexity and hinders scaling to high-dimensional goal spaces. In this work, we introduce an algorithm to train a flat (non-hierarchical) goal-conditioned policy by bootstrapping on subgoal-conditioned policies with advantage-weighted importance sampling. Our approach eliminates the need for a generative model over the (sub)goal space, which we find is key for scaling to high-dimensional control in large state spaces. We further show that existing hierarchical and bootstrapping-based approaches correspond to specific design choices within our derivation. Across a comprehensive suite of state- and pixel-based locomotion and manipulation benchmarks, our method matches or surpasses state-of-the-art offline GCRL algorithms and scales to complex, long-horizon tasks where prior approaches fail. Project page: https://johnlyzhou.github.io/saw/