Evolution Guided Generative Flow Networks
Generative Flow Networks (GFlowNets) are a family of probabilistic generative models that learn to sample compositional objects proportional to their rewards. One big challenge of GFlowNets is training them effectively when dealing with long time horizons and sparse rewards. To address this, we propose Evolution guided generative flow networks (EGFN), a simple but powerful augmentation to the GFlowNets training using Evolutionary algorithms (EA). Our method can work on top of any GFlowNets training objective, by training a set of agent parameters using EA, storing the resulting trajectories in the prioritized replay buffer, and training the GFlowNets agent using the stored trajectories. We present a thorough investigation over a wide range of toy and real-world benchmark tasks showing the effectiveness of our method in handling long trajectories and sparse rewards.
Code (0)
등록된 구현이 없습니다.
Tasks
Evolutionary AlgorithmsMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
FlowPIE: Test-Time Scientific Idea Evolution with Flow-Guided Literature Exploration
Scientific idea generation (SIG) is critical to AI-driven autonomous research, yet existing approaches are often constrained by a static retrieval-then-generation paradigm, leading to homogeneous and insufficiently diver…
Energy-Guided Flow Matching
Pixel-space generative models bypass lossy latent compression, yet necessitate joint learning of global structure and fine-grained details in a high-dimensional space. Standard flow matching interpolates noise toward a f…
Conditional Image GenerationText-to-Image GenerationAllo{SR}$^2$: Rectifying One-Step Super-Resolution to Stay Real via Allomorphic Generative Flows
Real-world image super-resolution (Real-SR) has been revolutionized by leveraging the powerful generative priors from Diffusion Models (DMs) and Flow Matching (FM). However, existing one-step methods typically replace Ga…
Image Super-ResolutionParetoFlow: Guided Flows in Multi-Objective Optimization
In offline multi-objective optimization (MOO), we leverage an offline dataset of designs and their associated labels to simultaneously minimize multiple objectives. This setting more closely mirrors complex real-world pr…
Bayesian OptimizationEvolutionary AlgorithmsVoicebox: Text-Guided Multilingual Universal Speech Generation at Scale
Large-scale generative models such as GPT and DALL-E have revolutionized the research community. These models not only generate high fidelity outputs, but are also generalists which can solve tasks not explicitly taught.…
In-Context LearningSpeech Synthesistext-to-speechText to Speech+1