arXiv Machine Learning
Aug 6
GFlowNet Training by Policy Gradients
arXiv:2408. 05885v3 Announce Type: replace Abstract: Generative Flow Networks (GFlowNets) have been shown effective to generate combinatorial objects with desired properties.
Partial GFlowNet: Accelerating Convergence in Large State Spaces via Strategic Partitioning
The paper introduces Partial GFlowNet, a method that partitions a large state space into overlapping partial state spaces to accelerate convergence of Generative Flow Networks. By restricting the actor’s exploration to these smaller regions and using a heuristic to switch between them, the approach enables efficient identification of high‑reward subregions. Experiments on popular datasets show that Partial GFlowNet converges faster, produces higher‑reward candidates, and improves diversity compared to existing methods.
Related stories
arXiv AI
Sep 3
Action abstractions for amortized sampling
The paper introduces a method that integrates action abstraction into policy optimization for reinforcement learning and generative flow networks. By iteratively identifying frequently used action subsequences in high‑reward trajectories and treating them as single high‑level actions, the approach expands the action space and improves sample efficiency. Experiments on synthetic and real‑world tasks show that this technique discovers diverse high‑reward states more effectively, especially on challenging exploration problems, and yields interpretable abstract actions that reflect the underlying reward structure.
arXiv Machine Learning
Aug 31
Trajectory balance: Improved credit assignment in GFlowNets
The paper introduces a new learning objective called trajectory balance for Generative Flow Networks (GFlowNets), aiming to improve credit assignment across long action sequences. It demonstrates that minimizing this objective yields a policy that samples exactly from the target distribution. Experiments on four domains show that trajectory balance enhances convergence, sample diversity, and robustness to long sequences and large action spaces.
arXiv AI
Jul 23
In-the-Flow Agentic System Optimization for Effective Planning and Tool Use
arXiv:2510. 05592v2 Announce Type: replace Abstract: Outcome-driven reinforcement learning has advanced reasoning in large language models (LLMs), but prevailing tool-augmented approaches train a single, monolithic policy that interleaves thoughts and tool calls under full context; this scales poorly with long horizons and diverse tools and generalizes weakly to new scenarios.
arXiv Machine Learning
Jul 16
GFlowRL: Scaling Distribution-Matching RL to Large Language Models
arXiv:2607. 13394v1 Announce Type: cross Abstract: Generative Flow Networks (GFlowNets) offer a promising alternative to reward-maximizing reinforcement learning (RL) for large reasoning models, encouraging diverse reasoning paths by matching reward distributions rather than collapsing to dominant modes.
arXiv Machine Learning
Aug 6
Stable GFlowNets with TV Monitoring and Probabilistic Guarantees
arXiv:2605. 01729v2 Announce Type: replace Abstract: Generative Flow Networks (GFlowNets) learn to sample states proportional to an unnormalized reward.
arXiv AI
Jun 24
FlowPipe: LLM-Enhanced Conditional Generative Flow Networks for Data Preparation Pipeline Construction
arXiv:2606. 24679v1 Announce Type: cross Abstract: Data preparation pipelines improve data quality in machine learning by transforming raw tables into learning-ready data through sequential cleaning and feature transformation operators.
arXiv Machine Learning
Sep 1
Amortizing intractable inference in large language models
arXiv:2310.04363v3 Announce Type: replace Abstract: Autoregressive large language models (LLMs) compress knowledge from their training data through next-token conditional distributions. This limits t...
arXiv Machine Learning
Sep 3
Act More, Decide Less: Skill-Guided Adaptive Action Chunking for Long-Horizon LLM Agents
The paper introduces SPACE, a method for enabling large language model agents to emit variable-length action chunks in long-horizon tasks. By distilling chunk-boundary supervision from programmatic skills derived from successful trajectories, SPACE overcomes the tendency of agents to either act one step at a time or commit to overly long sequences. Experiments on ALFWorld and ScienceWorld demonstrate that SPACE raises success rates by 7.0%–31.3% and cuts LLM decision rounds by up to 78.9%.
arXiv AI
Jun 16
Proximal Policy Optimization for Amortized Discrete Sampling
arXiv:2606. 15793v1 Announce Type: cross Abstract: This paper explores policy gradient algorithms for training stochastic policies to sample from structured discrete probability distributions under the Generative Flow Network (GFlowNet) framework.
arXiv Machine Learning
Sep 11
From Connectivity to Rewards: Dense Reward Learning with Directed State Graphs
The paper introduces Graph-Guided Quasimetric Dense Reward (G2QDR), a framework that learns a state connectivity model to predict pairwise connectivity strengths in asymmetric environments. These strengths are converted into scalar auxiliary dense rewards, offering continuous guidance across hierarchical levels. G2QDR can be integrated into any existing Goal-Conditioned Hierarchical Reinforcement Learning architecture and shows empirical performance improvements in sparse reward settings with modest computational cost.
arXiv Machine Learning
Jun 9
Latent Spherical Flow Policy for Reinforcement Learning with Combinatorial Actions
arXiv:2601. 22211v2 Announce Type: replace Abstract: Reinforcement learning (RL) with combinatorial action spaces remains challenging because feasible action sets are exponentially large and governed by complex feasibility constraints, making direct policy parameterization impractical.