Related papers: Discrete Probabilistic Inference as Control in Mul…
This paper studies Generative Flow Networks (GFlowNets), which learn to sample objects proportionally to a given reward function through the trajectory of state transitions. In this work, we observe that GFlowNets tend to under-exploit the…
In dynamic programming (DP) and reinforcement learning (RL), an agent learns to act optimally in terms of expected long-term return by sequentially interacting with its environment modeled by a Markov decision process (MDP). More generally…
Generative Flow Networks (GFlowNets or GFNs) are probabilistic models predicated on Markov flows, and they employ specific amortization algorithms to learn stochastic policies that generate compositional substances including biomolecules,…
Generative Flow Networks (GFlowNets) enable structured generation with inherent diversity, but existing sampling strategies often rely on weak guided exploration, slowing early discovery of high-reward candidates. In tasks such as molecular…
Achieving both accuracy and diverse reasoning remains challenging for Large Language Models (LLMs) in complex domains like mathematics. A key bottleneck is evaluating intermediate reasoning steps to guide generation without costly human…
Experimentally, it has been observed that humans and animals often make decisions that do not maximize their expected utility, but rather choose outcomes randomly, with probability proportional to expected utility. Probability matching, as…
Generative flow networks (GFlowNets), as an emerging technique, can be used as an alternative to reinforcement learning for exploratory control tasks. GFlowNet aims to generate distribution proportional to the rewards over terminating…
We propose FlowRL: matching the full reward distribution via flow balancing instead of maximizing rewards in large language model (LLM) reinforcement learning (RL). Recent advanced reasoning models adopt reward-maximizing methods (\eg, PPO…
While Markov chain Monte Carlo methods (MCMC) provide a general framework to sample from a probability distribution defined up to normalization, they often suffer from slow convergence to the target distribution when the latter is highly…
Distributional reinforcement learning (DRL) is a recent reinforcement learning framework whose success has been supported by various empirical studies. It relies on the key idea of replacing the expected return with the return distribution,…
Maximum entropy reinforcement learning (MaxEnt-RL) has become the standard approach to RL due to its beneficial exploration properties. Traditionally, policies are parameterized using Gaussian distributions, which significantly limits their…
Generative Flow Networks (GFlowNets) have been shown effective to generate combinatorial objects with desired properties. We here propose a new GFlowNet training framework, with policy-dependent rewards, that bridges keeping flow balance of…
We propose a simple, scalable algorithm for using stochastic interpolants to sample from unnormalized densities and for fine-tuning generative models. The approach, Tilt Matching, arises from a dynamical equation relating the flow matching…
Distributional reinforcement learning (DRL) enhances the understanding of the effects of the randomness in the environment by letting agents learn the distribution of a random return, rather than its expected value as in standard…
The incorporation of online reinforcement learning (RL) into diffusion and flow-based generative models has recently gained attention as a powerful paradigm for aligning model behavior with human preferences. By leveraging stochastic…
To date, distributional reinforcement learning (distributional RL) methods have exclusively focused on the discounted setting, where an agent aims to optimize a discounted sum of rewards over time. In this work, we extend distributional RL…
This paper studies the problem of steering the distribution of a discrete-time dynamical system from an initial distribution to a target distribution in finite time. The formulation is fully nonlinear, allowing the use of general control…
Reinforcement learning (RL) has become an effective way to improve prompt alignment and perceptual quality in diffusion and flow-matching generators. A critical step for applying online RL to flow matching is turning the deterministic…
Goal-Conditioned Reinforcement Learning (RL) problems often have access to sparse rewards where the agent receives a reward signal only when it has achieved the goal, making policy optimization a difficult problem. Several works augment…
Due to limited resources and fast economic growth, designing optimal transportation road networks with traffic simulation and validation in a cost-effective manner is vital for developing countries, where extensive manual testing is…