Generative Flow Networks as Entropy-Regularized RL
- URL: http://arxiv.org/abs/2310.12934v3
- Date: Sun, 25 Feb 2024 19:39:24 GMT
- Title: Generative Flow Networks as Entropy-Regularized RL
- Authors: Daniil Tiapkin, Nikita Morozov, Alexey Naumov, Dmitry Vetrov
- Abstract summary: generative flow networks (GFlowNets) are a method of training a policy to sample compositional objects with proportional probabilities to a given reward via a sequence of actions.
We demonstrate how the task of learning a generative flow network can be efficiently as an entropy-regularized reinforcement learning problem.
Contrary to previously reported results, we show that entropic RL approaches can be competitive against established GFlowNet training methods.
- Score: 4.857649518812728
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The recently proposed generative flow networks (GFlowNets) are a method of
training a policy to sample compositional discrete objects with probabilities
proportional to a given reward via a sequence of actions. GFlowNets exploit the
sequential nature of the problem, drawing parallels with reinforcement learning
(RL). Our work extends the connection between RL and GFlowNets to a general
case. We demonstrate how the task of learning a generative flow network can be
efficiently redefined as an entropy-regularized RL problem with a specific
reward and regularizer structure. Furthermore, we illustrate the practical
efficiency of this reformulation by applying standard soft RL algorithms to
GFlowNet training across several probabilistic modeling tasks. Contrary to
previously reported results, we show that entropic RL approaches can be
competitive against established GFlowNet training methods. This perspective
opens a direct path for integrating RL principles into the realm of generative
flow networks.
Related papers
- On Generalization for Generative Flow Networks [54.20924253330039]
Generative Flow Networks (GFlowNets) have emerged as an innovative learning paradigm designed to address the challenge of sampling from an unnormalized probability distribution.
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.
arXiv Detail & Related papers (2024-07-03T13:42:21Z) - Improving GFlowNets with Monte Carlo Tree Search [6.497027864860203]
Recent studies have revealed strong connections between GFlowNets and entropy-regularized reinforcement learning.
We propose to enhance planning capabilities of GFlowNets by applying Monte Carlo Tree Search (MCTS)
Our experiments demonstrate that this approach improves the sample efficiency of GFlowNet training and the generation fidelity of pre-trained GFlowNet models.
arXiv Detail & Related papers (2024-06-19T15:58:35Z) - Rectifying Reinforcement Learning for Reward Matching [12.294107455811496]
We establish a new connection between GFlowNets and policy evaluation for a uniform policy.
We propose a novel rectified policy evaluation algorithm, which achieves the same reward-matching effect as GFlowNets.
arXiv Detail & Related papers (2024-06-04T11:11:53Z) - Looking Backward: Retrospective Backward Synthesis for Goal-Conditioned GFlowNets [27.33222647437964]
Generative Flow Networks (GFlowNets) are amortized sampling methods for learning a policy to sequentially generate objects with probabilities to their rewards.
GFlowNets exhibit a remarkable ability to generate diverse sets of high-reward proportional objects, in contrast to standard reinforcement learning approaches.
Recent works have arisen for learning goal-conditioned GFlowNets to acquire various useful properties, aiming to train a single GFlowNet capable of achieving different goals as the task specifies.
We propose a novel method named Retrospective Backward Synthesis (RBS) to address these challenges. Specifically, RBS synthesizes a new backward trajectory
arXiv Detail & Related papers (2024-06-03T09:44:10Z) - Evolution Guided Generative Flow Networks [11.609895436955242]
Generative Flow Networks (GFlowNets) 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.
We propose Evolution guided generative flow networks (EGFN), a simple but powerful augmentation to the GFlowNets training using Evolutionary algorithms (EA)
arXiv Detail & Related papers (2024-02-03T15:28:53Z) - Pre-Training and Fine-Tuning Generative Flow Networks [61.90529626590415]
We introduce a novel approach for reward-free pre-training of GFlowNets.
By framing the training as a self-supervised problem, we propose an outcome-conditioned GFlowNet that learns to explore the candidate space.
We show that the pre-trained OC-GFN model can allow for a direct extraction of a policy capable of sampling from any new reward functions in downstream tasks.
arXiv Detail & Related papers (2023-10-05T09:53:22Z) - Stochastic Generative Flow Networks [89.34644133901647]
Generative Flow Networks (or GFlowNets) learn to sample complex structures through the lens of "inference as control"
Existing GFlowNets can be applied only to deterministic environments, and fail in more general tasks with dynamics.
This paper introduces GFlowNets, a new algorithm that extends GFlowNets to environments.
arXiv Detail & Related papers (2023-02-19T03:19:40Z) - Distributional GFlowNets with Quantile Flows [73.73721901056662]
Generative Flow Networks (GFlowNets) are a new family of probabilistic samplers where an agent learns a policy for generating complex structure through a series of decision-making steps.
In this work, we adopt a distributional paradigm for GFlowNets, turning each flow function into a distribution, thus providing more informative learning signals during training.
Our proposed textitquantile matching GFlowNet learning algorithm is able to learn a risk-sensitive policy, an essential component for handling scenarios with risk uncertainty.
arXiv Detail & Related papers (2023-02-11T22:06:17Z) - Learning GFlowNets from partial episodes for improved convergence and
stability [56.99229746004125]
Generative flow networks (GFlowNets) are algorithms for training a sequential sampler of discrete objects under an unnormalized target density.
Existing training objectives for GFlowNets are either local to states or transitions, or propagate a reward signal over an entire sampling trajectory.
Inspired by the TD($lambda$) algorithm in reinforcement learning, we introduce subtrajectory balance or SubTB($lambda$), a GFlowNet training objective that can learn from partial action subsequences of varying lengths.
arXiv Detail & Related papers (2022-09-26T15:44:24Z) - Generative Flow Networks for Discrete Probabilistic Modeling [118.81967600750428]
We present energy-based generative flow networks (EB-GFN)
EB-GFN is a novel probabilistic modeling algorithm for high-dimensional discrete data.
We show how GFlowNets can approximately perform large-block Gibbs sampling to mix between modes.
arXiv Detail & Related papers (2022-02-03T01:27:11Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.