Stochastic Generative Flow Networks
This addresses a problem for researchers and practitioners in machine learning by enabling GFlowNets to work in more general stochastic tasks, though it is incremental as it builds on existing GFlowNet frameworks.
The paper tackled the limitation of Generative Flow Networks (GFlowNets) to deterministic environments by introducing Stochastic GFlowNets, which extend them to handle stochastic dynamics, resulting in significant advantages over standard GFlowNets and other methods on various benchmarks.
Generative Flow Networks (or GFlowNets for short) are a family of probabilistic agents that learn to sample complex combinatorial structures through the lens of "inference as control". They have shown great potential in generating high-quality and diverse candidates from a given energy landscape. However, existing GFlowNets can be applied only to deterministic environments, and fail in more general tasks with stochastic dynamics, which can limit their applicability. To overcome this challenge, this paper introduces Stochastic GFlowNets, a new algorithm that extends GFlowNets to stochastic environments. By decomposing state transitions into two steps, Stochastic GFlowNets isolate environmental stochasticity and learn a dynamics model to capture it. Extensive experimental results demonstrate that Stochastic GFlowNets offer significant advantages over standard GFlowNets as well as MCMC- and RL-based approaches, on a variety of standard benchmarks with stochastic dynamics.