REVIEW 35 cited by
Flow Q-Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Flow Q-Learning
read the original abstract
We present flow Q-learning (FQL), a simple and performant offline reinforcement learning (RL) method that leverages an expressive flow-matching policy to model arbitrarily complex action distributions in data. Training a flow policy with RL is a tricky problem, due to the iterative nature of the action generation process. We address this challenge by training an expressive one-step policy with RL, rather than directly guiding an iterative flow policy to maximize values. This way, we can completely avoid unstable recursive backpropagation, eliminate costly iterative action generation at test time, yet still mostly maintain expressivity. We experimentally show that FQL leads to strong performance across 73 challenging state- and pixel-based OGBench and D4RL tasks in offline RL and offline-to-online RL. Project page: https://seohong.me/projects/fql/
Forward citations
Cited by 35 Pith papers
-
Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning
QGF performs test-time policy optimization for flow models in RL by guiding a behavior-cloned reference policy with value-function gradients, achieving strong results on high-dimensional offline RL benchmarks without ...
-
Sample-Efficient Diffusion-based Reinforcement Learning with Critic Guidance
CGPO integrates training-free critic guidance into diffusion denoising to produce high-Q actions as regression targets, yielding SOTA results on MuJoCo locomotion and successful Franka arm grasping.
-
Path-Coupled Bellman Flows for Distributional Reinforcement Learning
Path-Coupled Bellman Flows use source-consistent Bellman-coupled paths and a lambda-parameterized control-variate to learn return distributions via flow matching, improving fidelity and stability over prior DRL approaches.
-
Towards Efficient and Expressive Offline RL via Flow-Anchored Noise-conditioned Q-Learning
FAN achieves state-of-the-art offline RL performance on robotic tasks by anchoring flow policies and using single-sample noise-conditioned Q-learning, with proven convergence and reduced runtimes.
-
Preserve Support, Not Correspondence: Dynamic Routing for Offline Reinforcement Learning
DROL trains one-step offline RL actors via top-1 dynamic routing of dataset actions to latent candidates, enabling local improvements while preserving data support and retaining cheap inference.
-
Reinforcement Learning via Value Gradient Flow
VGF solves behavior-regularized RL by transporting particles from a reference distribution to the value-induced optimal policy via discrete value-guided gradient flow.
-
ScoRe-Flow: Complete Distributional Control via Score-Based Reinforcement Learning for Flow Matching
ScoRe-Flow achieves decoupled mean-variance control in stochastic flow matching by deriving a closed-form score for drift modulation plus learned variance, yielding faster RL convergence and higher success rates on lo...
-
EXPO: Stable Reinforcement Learning with Expressive Policies
EXPO stabilizes online RL for expressive policies by training a base policy with imitation and using a lightweight Gaussian edit policy to select higher-value actions on the fly for sampling and TD backups.
-
Steering Your Diffusion Policy with Latent Space Reinforcement Learning
DSRL steers pretrained diffusion policies for robotics by applying RL to their latent noise inputs, achieving sample-efficient real-world adaptation with only black-box access.
-
Source-Lifted Flow Matching for Intervenable Multimodal Imitation
Orthogonal Source Lifting makes flow-matching imitation intervenable by selecting only the source endpoint, changing future routes in 91.1% of matched-prefix tests while keeping free-deployment performance strong.
-
NFTR: From Provable Mode-Averaging to Geodesic Subgoal Selection in Offline Goal-Conditioned RL
Normalizing-flow subgoal policies plus triangle-slack reweighting provably avoid Gaussian mode-averaging and filter lucky transitions in offline hierarchical GCRL.
-
Good Rankers, Bad Objectives: Bilinear Contrastive Critics under Expressive Policy Search
Bilinear contrastive critics remain good compatibility rankers but are unsafe to maximize for action selection; cosine bounding does not fix value decalibration, while Bellman TD-Q does.
-
Do You Really Need to Pretrain Q-Functions for Online RL Fine-Tuning?
Naive Q-pretraining rarely helps online RL fine-tuning of a pretrained policy; IPE’s multi-policy rollouts close the Qπbase vs Qπ*RL gap and raise success ~1.26×.
-
Fast and Highly Expressive Policy Learning for Offline Reinforcement Learning via Bootstrapped Flow Q-Learning
BFQ enables single-step noise-to-action mapping in offline RL by dividing flow-path displacements into bootstrappable short-range components learned from marginal velocity.
-
GenPO++: Generative Policy Optimization with Jacobian-free Likelihood Ratios
GenPO++ achieves exact Jacobian-free likelihood ratio computation for generative flow policies by embedding history states as auxiliary memory in a high-order reversible ODE solver.
-
Path-Coupled Bellman Flows for Distributional Reinforcement Learning
PCBF learns return distributions via source-consistent Bellman-coupled paths with shared noise and λ-parameterized control variates, reporting improved fidelity and stability on MRPs, OGBench, and D4RL.
-
Long-Horizon Q-Learning: Accurate Value Learning via n-Step Inequalities
LQL stabilizes Q-learning by penalizing violations of n-step action-sequence lower bounds with a hinge loss computed from standard network outputs.
-
Long-Horizon Q-Learning: Accurate Value Learning via n-Step Inequalities
LQL turns n-step action-sequence lower bounds into a practical hinge-loss stabilizer for off-policy Q-learning without extra networks or forward passes.
-
Adaptive Q-Chunking for Offline-to-Online Reinforcement Learning
Adaptive Q-Chunking selects optimal action chunk sizes at each state via normalized advantage comparisons to outperform fixed chunk sizes in offline-to-online RL on robot benchmarks.
-
Towards Efficient and Expressive Offline RL via Flow-Anchored Noise-conditioned Q-Learning
FAN simplifies expressive flow policies and distributional critics in offline RL via single-iteration behavior regularization and single-sample noise conditioning to claim SOTA performance with lower training and infe...
-
Model-Based Proactive Cost Generation for Learning Safe Policies Offline with Limited Violation Data
PROCO generates synthetic unsafe samples via model-based rollouts and LLM-grounded costs to enable safer policy learning from offline datasets containing few or no violations.
-
Truncated Rectified Flow Policy for Reinforcement Learning with One-Step Sampling
TRFP combines rectified flow models with truncation to support multimodal policies in MaxEnt RL while allowing fast one-step sampling and stable training.
-
From Prior to Pro: Efficient Skill Mastery via Distribution Contractive RL Finetuning
Residual off-policy RL with selective BC regularization and value-guided sampling contracts a pretrained generative robot policy around successful actions, reaching high success on hard long-horizon tasks from pixels ...
-
What Does Flow Matching Bring To TD Learning?
Flow matching critics outperform monolithic ones in RL by 2x performance and 5x sample efficiency via test-time error recovery through integration and multi-point velocity supervision that preserves feature plasticity.
-
How Does the Lagrangian Guide Safe Reinforcement Learning through Diffusion Models?
ALGD augments the Lagrangian to locally convexify the energy landscape in diffusion models, stabilizing safe RL training and generation without changing optimal policies.
-
FM-IRL: Flow-Matching for Reward Modeling and Policy Regularization in Reinforcement Learning
An online imitation-learning method uses a flow-matching teacher's class-conditional loss as a reward and a regularizer to train a simple MLP policy, beating cloning and adversarial-imitation baselines on five of six tasks.
-
Reinforcement Learning with Action Chunking
Q-chunking improves offline-to-online RL sample efficiency on long-horizon sparse-reward manipulation tasks by applying action chunking to TD learning.
-
Offline RL with Hierarchical Action Chunking
HiQC, a hierarchy of latent subgoal planning and chunked action execution, achieves the best OGBench aggregate score (53%) and an O(sqrt(T/k)) error bound under a bootstrap-chain model.
-
Reinforcement Learning from Cross-domain Videos with Video Prediction Model
XIPER creates a reward signal for cross-domain video imitation learning by training a video prediction model that maps agent views to the expert domain and scoring prediction likelihood.
-
Lagrangian Perturbation Diffusion Steering: Latent Reinforcement Learning for Generative Policies
LP-DS improves generative policies for imitation and RL by optimizing latent noise perturbations with a constrained Lagrangian objective, showing up to 25% better returns on manipulation and locomotion tasks.
-
Efficient Hierarchical Implicit Flow Q-learning for Offline Goal-conditioned Reinforcement Learning
Proposes mean flow policies and LeJEPA loss to overcome Gaussian policy limits and weak subgoal generation in hierarchical offline GCRL, reporting strong results on OGBench state and pixel tasks.
-
Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agents
Simplicial embeddings — group-wise softmax feature layers — improve sample efficiency and final performance of FastTD3, FastSAC, and PPO across continuous- and discrete-control benchmarks at no meaningful runtime cost.
-
Value Flows
Value Flows fits the full return distribution in RL with a flow-matching critic and reweights its learning objective by estimated return variance; the central theoretical guarantee does not follow from the stated equations.
-
Intention-Conditioned Flow Occupancy Models
InFOM applies flow matching to model intention-conditioned occupancy measures for RL pre-training, reporting 1.8x median return gains and 36% higher success rates on benchmarks.
-
ReFPO: Reflow Regularization for Flow Matching Policy Gradients
ReFPO adds explicit Reflow regularization to FPO, stabilizing PPO-style training and supporting high-fidelity one-step inference across GridWorld, MuJoCo, and Humanoid tasks.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.