Search Results for author:
Found 12 papers, 9 papers with code
On Generalization for Generative Flow Networks
This paper attempts to formalize generalization in the context of GFlowNets, to link generalization with stability, and also to design experiments that assess the capacity of these models to uncover unseen parts of the reward function.
PORT: Preference Optimization on Reasoning Traces
This paper proposes using preference optimization methods on Chain-of-Thought steps in order to improve the reasoning performances of language models.
BatchGFN: Generative Flow Networks for Batch Active Learning
We introduce BatchGFN -- a novel approach for pool-based active learning that uses generative flow networks to sample sets of data points proportional to a batch reward.
Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks
We present the Minigrid and Miniworld libraries which provide a suite of goal-oriented 2D and 3D environments.
torchgfn: A PyTorch GFlowNet library
The growing popularity of generative flow networks (GFlowNets or GFNs) from a range of researchers with diverse backgrounds and areas of expertise necessitates a library which facilitates the testing of new features such as training losses that can be easily compared to standard benchmark implementations, or on a set of common environments.
A theory of continuous generative flow networks
Generative flow networks (GFlowNets) are amortized variational inference algorithms that are trained to sample from unnormalized target distributions over compositional objects.
GFlowOut: Dropout with Generative Flow Networks
These methods face two important challenges: (a) the posterior distribution over masks can be highly multi-modal which can be difficult to approximate with standard variational inference and (b) it is not trivial to fully utilize sample-dependent information and correlation among dropout masks to improve posterior estimation.
GFlowNets and variational inference
This paper builds bridges between two families of probabilistic algorithms: (hierarchical) variational inference (VI), which is typically used to model distributions over continuous spaces, and generative flow networks (GFlowNets), which have been used for distributions over discrete structures such as graphs.
GFlowNet Foundations
Generative Flow Networks (GFlowNets) have been introduced as a method to sample a diverse set of candidates in an active learning context, with a training objective that makes them approximately sample in proportion to a given reward function.
DEUP: Direct Epistemic Uncertainty Prediction
Epistemic Uncertainty is a measure of the lack of knowledge of a learner which diminishes with more evidence.
Mastering Rate based Curriculum Learning
Recent automatic curriculum learning algorithms, and in particular Teacher-Student algorithms, rely on the notion of learning progress, making the assumption that the good next tasks are the ones on which the learner is making the fastest progress or digress.
BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning
Allowing humans to interactively train artificial agents to understand language instructions is desirable for both practical and scientific reasons, but given the poor data efficiency of the current learning methods, this goal may require substantial research efforts.
