# Looking Backward: Retrospective Backward Synthesis for Goal-Conditioned GFlowNets

arXiv: https://arxiv.org/abs/2406.01150 · HTML: https://mlsanity.com/paper/2406.01150/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in RL with diffusion and flow models, one of 15 directions in Deep reinforcement learning methods.
- Builds on 52 of its 73 references that are in the map.
- First posted on arXiv 3 Jun 2024.

## Placed in

- Deep reinforcement learning methods / [RL with diffusion and flow models](https://mlsanity.com/deeprl/rl-with-diffusion-and-flow-models/)

## Builds on (most cited first, 30 of 52)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [Prioritized Experience Replay](https://mlsanity.com/paper/1511.05952/) (2015)
- [Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels](https://mlsanity.com/paper/2004.13649/) (2020)
- [Empirical Evaluation of Rectified Activations in Convolutional Network](https://mlsanity.com/paper/1505.00853/) (2015)
- [Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation](https://mlsanity.com/paper/2106.04399/) (2021)
- [GFlowNet Foundations](https://mlsanity.com/paper/2111.09266/) (2021)
- [Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents](https://mlsanity.com/paper/1709.06009/) (2017)
- [Contrastive Learning as Goal-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2206.07568/) (2022)
- [Trajectory balance: Improved credit assignment in GFlowNets](https://mlsanity.com/paper/2201.13259/) (2022)
- [Biological Sequence Design with GFlowNets](https://mlsanity.com/paper/2203.04115/) (2022)
- [Goal-conditioned Imitation Learning](https://mlsanity.com/paper/1906.05838/) (2019)
- [Goal-Conditioned Reinforcement Learning: Problems and Solutions](https://mlsanity.com/paper/2201.08299/) (2022)
- [Bayesian Structure Learning with Generative Flow Networks](https://mlsanity.com/paper/2202.13903/) (2022)
- [Planning with Goal-Conditioned Policies](https://mlsanity.com/paper/1911.08453/) (2019)
- [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)
- [Learning GFlowNets from partial episodes for improved convergence and stability](https://mlsanity.com/paper/2209.12782/) (2022)
- [C-Learning: Learning to Achieve Goals via Recursive Classification](https://mlsanity.com/paper/2011.08909/) (2020)
- [Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RL](https://mlsanity.com/paper/2202.04478/) (2022)
- [Better Training of GFlowNets with Local Credit and Incomplete Trajectories](https://mlsanity.com/paper/2302.01687/) (2023)
- [One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL](https://mlsanity.com/paper/2010.14484/) (2020)
- [Towards Understanding and Improving GFlowNet Training](https://mlsanity.com/paper/2305.07170/) (2023)
- [Robust Scheduling with GFlowNets](https://mlsanity.com/paper/2302.05446/) (2023)
- [How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via f-Advantage Regression](https://mlsanity.com/paper/2206.03023/) (2022)
- [Generative Flow Networks as Entropy-Regularized RL](https://mlsanity.com/paper/2310.12934/) (2023)
- [GFlowNets for AI-Driven Scientific Discovery](https://mlsanity.com/paper/2302.00615/) (2023)
- [Generative Augmented Flow Networks](https://mlsanity.com/paper/2210.03308/) (2022)

## Built on by (most cited first, 8 of 8)

- [FlowRL: Matching Reward Distributions for LLM Reasoning](https://mlsanity.com/paper/2509.15207/) (2025)
- [Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples](https://mlsanity.com/paper/2406.05673/) (2024)
- [Learning to Sample Effective and Diverse Prompts for Text-to-Image Generation](https://mlsanity.com/paper/2502.11477/) (2025)
- [Optimizing Backward Policies in GFlowNets via Trajectory Likelihood Maximization](https://mlsanity.com/paper/2410.15474/) (2024)
- [GFlowNet Pretraining with Inexpensive Rewards](https://mlsanity.com/paper/2409.09702/) (2024)
- [Pretraining Generative Flow Networks with Inexpensive Rewards for Molecular Graph Generation](https://mlsanity.com/paper/2503.06337/) (2025)
- [Rooted Absorbed Prefix Trajectory Balance with Submodular Replay for GFlowNet Training](https://mlsanity.com/paper/2603.00454/) (2026)
- [Stable GFlowNets with TV Monitoring and Probabilistic Guarantees](https://mlsanity.com/paper/2605.01729/) (2026)

## Abstract (arXiv)

Generative Flow Networks (GFlowNets), a new family of probabilistic samplers, have demonstrated remarkable capabilities to generate diverse sets of high-reward candidates, in contrast to standard return maximization approaches (e.g., reinforcement learning) which often converge to a single optimal solution. Recent works have focused on developing goal-conditioned GFlowNets, which aim to train a single GFlowNet capable of achieving different outcomes as the task specifies. However, training such models is challenging due to extremely sparse rewards, particularly in high-dimensional problems. Moreover, previous methods suffer from the limited coverage of explored trajectories during training, which presents more pronounced challenges when only offline data is available. In this work, we propose a novel method called Retrospective Backward Synthesis (RBS) to address these critical problems. Specifically, RBS synthesizes new backward trajectories in goal-conditioned GFlowNets to enrich training trajectories with enhanced quality and diversity, thereby introducing copious learnable signals for effectively tackling the sparse reward problem. Extensive empirical results show that our method improves sample efficiency by a large margin and outperforms strong baselines on various standard evaluation benchmarks.