Flow-GRPO is the first online RL method for flow matching models, raising GenEval accuracy from 63% to 95% and text-rendering accuracy from 59% to 92% with little reward hacking.
super hub Mixed citations
Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning
Mixed citation behavior. Most common role is background (65%).
100
Pith papers citing it
166
external citations · Pith
Background
65% of classified citations
abstract
In this paper, we aim to develop a simple and scalable reinforcement learning algorithm that uses standard supervised learning methods as subroutines. Our goal is an algorithm that utilizes only simple and convergent maximum likelihood loss functions, while also being able to leverage off-policy data. Our proposed approach, which we refer to as advantage-weighted regression (AWR), consists of two standard supervised learning steps: one to regress onto target values for a value function, and another to regress onto weighted target actions for the policy. The method is simple and general, can accommodate continuous and discrete actions, and can be implemented in just a few lines of code on top of standard supervised learning methods. We provide a theoretical motivation for AWR and analyze its properties when incorporating off-policy data from experience replay. We evaluate AWR on a suite of standard OpenAI Gym benchmark tasks, and show that it achieves competitive performance compared to a number of well-established state-of-the-art RL algorithms. AWR is also able to acquire more effective policies than most off-policy algorithms when learning from purely static datasets with no additional environmental interactions. Furthermore, we demonstrate our algorithm on challenging continuous control tasks with highly complex simulated characters.
hub tools
citation-role summary
background 11
method 6
citation-polarity summary
claims ledger
- abstract In this paper, we aim to develop a simple and scalable reinforcement learning algorithm that uses standard supervised learning methods as subroutines. Our goal is an algorithm that utilizes only simple and convergent maximum likelihood loss functions, while also being able to leverage off-policy data. Our proposed approach, which we refer to as advantage-weighted regression (AWR), consists of two standard supervised learning steps: one to regress onto target values for a value function, and another to regress onto weighted target actions for the policy. The method is simple and general, can ac
co-cited works
representative citing papers
IQL achieves policy improvement in offline RL by implicitly estimating optimal action values through state-conditional upper expectiles of value functions, without querying Q-functions on out-of-distribution actions.
Decision Transformer casts RL as autoregressive sequence modeling conditioned on desired returns, past states and actions, matching or exceeding offline RL baselines on Atari, Gym and Key-to-Door tasks.
D4RL supplies new offline RL benchmarks and datasets from expert and mixed sources to expose weaknesses in existing algorithms and standardize evaluation.
UCOB uses local return comparisons between skill and no-skill views to choose which view teaches the other, improving agent training on ALFWorld and WebShop.
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 additional policy training.
Dual Advantage Fields converts bilinear dual value models into local advantage scores via learned action-effect models, equaling the goal-conditioned Bellman advantage under realizability and improving aggregate metrics on OGBench locomotion, manipulation, and puzzle tasks.
Introduces a state-aligned latent actor-critic framework that lets diffusion models act as their own timestep-conditioned value functions for trajectory-level RL post-training and inference steering.
FAV aligns few-step generative models by amortizing SVGD updates from reward-tilted sampling into generator parameters via fixed-point regression, requiring only sample access, and shows outperformance on robotics tasks plus scaling on image generators.
RankE co-evolves AR policy and decoder via alternating ranking optimization, improving both FID and CLIP scores on LlamaGen-XL and Janus-Pro where policy-only RL degrades FID.
Proposes latent analogies and analogy transduction to enable compositional generalization to unseen goal-context pairs in offline GCRL, outperforming trajectory-stitching baselines on manipulation tasks.
VPD frames language feedback learning as variational EM so the teacher policy refines itself via trust-region updates on outcomes while the student learns dense token distributions on its own rollouts, outperforming fixed-teacher baselines on reasoning and code tasks.
CPQL adapts the multi-step Peng's Q(λ) operator for conservative offline value estimation, achieving performance guarantees and empirical gains over single-step baselines on D4RL while supporting offline-to-online fine-tuning.
Switching successor measures extend classical successor measures to enable hierarchical zero-shot RL via the FB π-Switch algorithm that extracts subgoal-selection and control policies from forward-backward representations.
Introduces Block-R1 benchmark, Block-R1-41K dataset, and a conflict score to handle domain-specific optimal block sizes in RL post-training of diffusion LLMs.
AB-SID-iVAR enables Gaussian process active learning for self-induced Boltzmann distributions by closed-form approximation of the target, with high-probability error vanishing guarantees and empirical gains on PES and drug discovery tasks.
Reference-sampled weighted SFT with prompt-normalized Boltzmann weights induces the same policy as fixed-reference KL-regularized RLVR, with BOLT as the estimator and a finite one-shot error decomposition separating coverage, variance, and other terms.
SVL reframes goal-conditioned RL as a survival analysis problem, expressing the value function as a discounted sum of survival probabilities trained via maximum likelihood.
SOLACE improves text-to-image generation by using intrinsic self-confidence rewards from noise reconstruction accuracy during reinforcement learning post-training without external supervision.
GC-TTT adapts goal-conditioned policies at test time by fine-tuning on self-supervised selected goal-related offline data, yielding performance gains in loco-navigation and manipulation tasks.
GiGPO adds a hierarchical grouping mechanism to group-based RL so that LLM agents receive both global trajectory and local step-level credit signals, yielding >12% gains on ALFWorld and >9% on WebShop over GRPO while keeping the same rollout and memory footprint.
KTO aligns LLMs by directly maximizing prospect-theoretic utility on binary signals and matches or exceeds preference-based methods like DPO from 1B to 30B parameters.
DPO derives the optimal policy directly from human preferences via a reparameterized reward model, solving the RLHF objective with only a binary classification loss and no sampling or separate reward model.
VIP learns a visual embedding from human videos whose distance defines dense, smooth rewards for arbitrary goal-image robot tasks without task-specific fine-tuning.
citing papers explorer
-
Flow-GRPO: Training Flow Matching Models via Online RL
Flow-GRPO is the first online RL method for flow matching models, raising GenEval accuracy from 63% to 95% and text-rendering accuracy from 59% to 92% with little reward hacking.
-
Offline Reinforcement Learning with Implicit Q-Learning
IQL achieves policy improvement in offline RL by implicitly estimating optimal action values through state-conditional upper expectiles of value functions, without querying Q-functions on out-of-distribution actions.
-
Decision Transformer: Reinforcement Learning via Sequence Modeling
Decision Transformer casts RL as autoregressive sequence modeling conditioned on desired returns, past states and actions, matching or exceeding offline RL baselines on Atari, Gym and Key-to-Door tasks.
-
D4RL: Datasets for Deep Data-Driven Reinforcement Learning
D4RL supplies new offline RL benchmarks and datasets from expert and mixed sources to expose weaknesses in existing algorithms and standardize evaluation.
-
UCOB: Learning to Utilize and Evolve Agentic Skills via Credit-Aware On-Policy Bidirectional Self-Distillation
UCOB uses local return comparisons between skill and no-skill views to choose which view teaches the other, improving agent training on ALFWorld and WebShop.
-
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 additional policy training.
-
Dual Advantage Fields
Dual Advantage Fields converts bilinear dual value models into local advantage scores via learned action-effect models, equaling the goal-conditioned Bellman advantage under realizability and improving aggregate metrics on OGBench locomotion, manipulation, and puzzle tasks.
-
Explicit Critic Guidance for Aligning Diffusion Models
Introduces a state-aligned latent actor-critic framework that lets diffusion models act as their own timestep-conditioned value functions for trajectory-level RL post-training and inference steering.
-
Aligning Few-Step Generative Models by Amortizing Sample-based Variational Inference
FAV aligns few-step generative models by amortizing SVGD updates from reward-tilted sampling into generator parameters via fixed-point regression, requiring only sample access, and shows outperformance on robotics tasks plus scaling on image generators.
-
RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution
RankE co-evolves AR policy and decoder via alternating ranking optimization, improving both FID and CLIP scores on LlamaGen-XL and Janus-Pro where policy-only RL degrades FID.
-
Compositional Transduction with Latent Analogies for Offline Goal-Conditioned Reinforcement Learning
Proposes latent analogies and analogy transduction to enable compositional generalization to unseen goal-context pairs in offline GCRL, outperforming trajectory-stitching baselines on manipulation tasks.
-
Learning from Language Feedback via Variational Policy Distillation
VPD frames language feedback learning as variational EM so the teacher policy refines itself via trust-region updates on outcomes while the student learns dense token distributions on its own rollouts, outperforming fixed-teacher baselines on reasoning and code tasks.
-
Peng's Q($\lambda$) for Conservative Value Estimation in Offline Reinforcement Learning
CPQL adapts the multi-step Peng's Q(λ) operator for conservative offline value estimation, achieving performance guarantees and empirical gains over single-step baselines on D4RL while supporting offline-to-online fine-tuning.
-
Switching Successor Measures for Hierarchical Zero-shot Reinforcement Learning
Switching successor measures extend classical successor measures to enable hierarchical zero-shot RL via the FB π-Switch algorithm that extracts subgoal-selection and control policies from forward-backward representations.
-
Block-R1: Rethinking the Role of Block Size in Multi-domain Reinforcement Learning for Diffusion Large Language Models
Introduces Block-R1 benchmark, Block-R1-41K dataset, and a conflict score to handle domain-specific optimal block sizes in RL post-training of diffusion LLMs.
-
Active Learning for Gaussian Process Regression Under Self-Induced Boltzmann Weights
AB-SID-iVAR enables Gaussian process active learning for self-induced Boltzmann distributions by closed-form approximation of the target, with high-probability error vanishing guarantees and empirical gains on PES and drug discovery tasks.
-
Reference-Sampled Boltzmann Projection for KL-Regularized RLVR: Target-Matched Weighted SFT, Finite One-Shot Gaps, and Policy Mirror Descent
Reference-sampled weighted SFT with prompt-normalized Boltzmann weights induces the same policy as fixed-reference KL-regularized RLVR, with BOLT as the estimator and a finite one-shot error decomposition separating coverage, variance, and other terms.
-
SVL: Goal-Conditioned Reinforcement Learning as Survival Learning
SVL reframes goal-conditioned RL as a survival analysis problem, expressing the value function as a discounted sum of survival probabilities trained via maximum likelihood.
-
Improving Text-to-Image Generation with Intrinsic Self-Confidence Rewards
SOLACE improves text-to-image generation by using intrinsic self-confidence rewards from noise reconstruction accuracy during reinforcement learning post-training without external supervision.
-
Test-time Offline Reinforcement Learning on Goal-related Experience
GC-TTT adapts goal-conditioned policies at test time by fine-tuning on self-supervised selected goal-related offline data, yielding performance gains in loco-navigation and manipulation tasks.
-
Group-in-Group Policy Optimization for LLM Agent Training
GiGPO adds a hierarchical grouping mechanism to group-based RL so that LLM agents receive both global trajectory and local step-level credit signals, yielding >12% gains on ALFWorld and >9% on WebShop over GRPO while keeping the same rollout and memory footprint.
-
KTO: Model Alignment as Prospect Theoretic Optimization
KTO aligns LLMs by directly maximizing prospect-theoretic utility on binary signals and matches or exceeds preference-based methods like DPO from 1B to 30B parameters.
-
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
DPO derives the optimal policy directly from human preferences via a reparameterized reward model, solving the RLHF objective with only a binary classification loss and no sampling or separate reward model.
-
VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training
VIP learns a visual embedding from human videos whose distance defines dense, smooth rewards for arbitrary goal-image robot tasks without task-specific fine-tuning.
-
Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning
Diffusion-QL uses conditional diffusion models as expressive policies in offline RL by coupling behavior cloning with Q-value maximization, achieving SOTA on most D4RL tasks.
-
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.
-
Controllable Sim Agents with Behavior Latents
CNeVA combines variational behavior latents with rectified-flow generators and soft eligibility to deliver controllable yet realistic traffic simulation on Waymo data.
-
Active-GRPO: Adaptive Imitation and Self-Improving Reasoning for Molecular Optimization
Active-GRPO reaches 0.1773 average SRxSim on TOMG-Bench MOLOPT by adaptively switching between imitation and self-reinforcement while upgrading references, outperforming GRPO and RePO.
-
Freeform Preference Learning for Robotic Manipulation
FPL trains a language-conditioned reward model from per-axis human preferences and a reward-conditioned policy, reporting 38-point average success gains over sparse-reward and binary-preference baselines on six manipulation tasks.
-
STEAM: Self-Supervised Temporal Ensemble Advantage Modeling for Real-World Robot Learning
STEAM learns advantages from expert trajectories via self-supervised temporal ensemble modeling to improve policy learning on real robot tasks like bimanual folding and pick-and-place.
-
Beyond Monotonic Progress: Retry-Supervised Value Learning for Robot Imitation
Sparse retry keypoints plus pairwise preference learning yield mistake-sensitive values that reweight mixed-quality demos and raise real-robot imitation success over progress-based baselines.
-
Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning
G2PO transforms linear trajectories into graphs, aggregates identical states for lower-variance value estimates, and uses edge-centric TD standardization, reporting up to 22.2% gains over GRPO on WebShop, ALFWorld, and AppWorld.
-
FlowDPG: Deterministic Policy Gradient on Flow Matching Policies for Real-World Manipulation
FlowDPG distills critic gradients into flow matching velocity fields to enable BPTT-free DDPG-style policy improvement and reports 92% success on a real-world dual-arm AirPods assembly task.
-
Horizon Adaptive Offline Policy Learning via Value Stitching
VAST learns a horizon-adaptive auxiliary value function and stitching policy to compose variable-length returns for improved offline policy optimization on long-horizon tasks.
-
SARM2: Multi-Task Stage Aware Reward Modeling for Self Improving Robotic Manipulation
SARM2 presents RM, a multi-task stage-aware reward model achieving 80% lower value-estimation MSE, which when used in SPIRAL boosts manipulation task success from ~50% to near-perfect on several benchmarks.
-
Counterfactual Transport Flows for Offline Conservative Trajectory Refinement
Counterfactual transport flows enable conservative, instance-specific trajectory refinement in offline RL by constructing local preference pairs in latent space from offline data and learning refinement directions controlled by a strength parameter.
-
Plug-and-Play Guidance for Discrete Diffusion Models via Gradient-Informed Logit Correction
GILC guides discrete diffusion at inference time by adding reward gradients to the prediction logits, matching or beating fine-tuned baselines on DNA, protein, and molecule generation tasks without retraining.
-
Consolidating Rewarded Perturbations for LLM Post-Training
CoRP consolidates reward-weighted perturbations into a single model via low-rank structure, improving base LLMs by 8.1 points on average while using one-tenth the budget of prior ensembles and one forward pass.
-
DRIFT: Decoupled Rollouts and Importance-Weighted Fine-Tuning for Efficient Multi-Turn Optimization
DRIFT achieves multi-turn RL performance via offline importance-weighted SFT by leveraging the equivalence of KL-regularized RL to weighted supervised learning.
-
FLAG: Flow Policy MaxEnt-RL by Latent Augmented Guidance
FLAG augments state space with flow latent variable to optimize a proxy MaxEnt-RL objective, enabling expressive policies with limited importance samples in high-dimensional control.
-
Moment Matching Q-Learning
MoMa QL uses MMD moment matching to enforce distribution-level convergence of conditional score functions in flow-based RL policies for improved sampling efficiency.
-
SPAR: Support-Preserving Action Rectification
SPAR anchors policy learning to a frozen BC policy for residual rectification and introduces latent self-imitation to eliminate manifold drift, achieving SOTA on D4RL.
-
Latent Representation Alignment for Offline Goal-Conditioned Reinforcement Learning
LAVL combines latent-representation value generalization with hierarchical planning to reduce erroneous generalization in offline GCRL and outperforms prior methods on 20 of 22 OGBench datasets.
-
How Neural Reward Models Learn Features for Policy Optimization: A Single-Index Analysis
In a Gaussian single-index model, neural reward models recover the hidden direction for β1 above an O(1) threshold and provide tilted-policy value-gap bounds for label-weighted and surrogate-weighted exponential fits.
-
Goal-Conditioned Agents that Learn Everything All at Once
LEO enables efficient all-goals learning in goal-conditioned RL by jointly predicting for all goals in one network pass, yielding >250x speedup over relabelling and better performance on Craftax.
-
Reinforcing Human Behavior Simulation via Verbal Feedback
DITTO uses RL with verbal feedback to train LLMs for human behavior simulation, reporting 36% average gains over base models and outperforming GPT-5.4 on 6 of 10 SOUL benchmark tasks.
-
Offline Reinforcement Learning with Universal Horizon Models
Universal horizon models extend geometric horizon models to arbitrary horizons and apply winsorized distributions for stable offline RL value learning, outperforming baselines on 100 OGBench tasks.
-
Decaf: Improving Neural Decompilation with Automatic Feedback and Search
Decaf uses compiler feedback and search to improve neural decompilation, boosting semantic success rate from 26.0% to 83.9% on ExeBench Real -O2 split.
-
Drifting Field Policy: A One-Step Generative Policy via Wasserstein Gradient Flow
DFP is a one-step generative policy using Wasserstein gradient flow on a drifting model backbone, with a top-K behavior cloning surrogate, that reaches SOTA on Robomimic and OGBench manipulation tasks.
-
Implicit Preference Alignment for Human Image Animation
IPA aligns animation models for superior hand quality via implicit reward maximization on self-generated samples plus hand-focused local optimization, avoiding expensive paired data.