Drift Lipschitz budget K yields 1/K value approximation for diffusion policies, with matching lower bound, and finite-sample rates Õ(n^{-2/(m+6)}) (generic) or Õ(n^{-2/(m+4)}) (dissipative).
hub
Policy representation via diffusion probability model for reinforcement learning
25 Pith papers cite this work. Polarity classification is still indexing.
25
Pith papers citing it
abstract
Popular reinforcement learning (RL) algorithms tend to produce a unimodal policy distribution, which weakens the expressiveness of complicated policy and decays the ability of exploration. The diffusion probability model is powerful to learn complicated multimodal distributions, which has shown promising and potential applications to RL. In this paper, we formally build a theoretical foundation of policy representation via the diffusion probability model and provide practical implementations of diffusion policy for online model-free RL. Concretely, we character diffusion policy as a stochastic process, which is a new approach to representing a policy. Then we present a convergence guarantee for diffusion policy, which provides a theory to understand the multimodality of diffusion policy. Furthermore, we propose the DIPO which is an implementation for model-free online RL with DIffusion POlicy. To the best of our knowledge, DIPO is the first algorithm to solve model-free online RL problems with the diffusion model. Finally, extensive empirical results show the effectiveness and superiority of DIPO on the standard continuous control Mujoco benchmark.
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
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.
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.
Flow map policies enable fast one-step inference for flow-based RL policies, and FMQ provides an optimal closed-form Q-guided target for offline-to-online adaptation under trust-region constraints, achieving SOTA performance.
MATCH trains hybrid position-force RL policies that achieve up to 10% higher success rates and 5x fewer breaks than pose-only policies in fragile peg-in-hole tasks under localization uncertainty, with strong sim-to-real results.
VGF solves behavior-regularized RL by transporting particles from a reference distribution to the value-induced optimal policy via discrete value-guided gradient flow.
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.
Reversal Q-Learning (RQL) proposes reversing flows for virtual trajectories and bias-variance reduction in an expanded MDP to train flow policies, reporting best average performance on 50 simulated robotic tasks versus prior flow-based offline RL methods.
Q-VGM offline RL fine-tuning converts critic Q-gradients into residual velocity targets for flow-matching VLAs, raising LIBERO success from 75.0% to 92.5%.
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.
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.
SOM is an actor-critic algorithm that constructs the target velocity field for one-step MeanFlow policies directly from the Q-function via score estimation and probability flow ODE, achieving claimed SOTA on locomotion tasks with reduced training and inference time.
Recasts sampling-based nonconvex optimization as smoothed gradient descent to obtain non-asymptotic convergence guarantees and introduces the DIDA annealed algorithm that converges to the global optimum.
Decentralized diffusion policies trained with importance sampling score matching enhance exploration and performance in cooperative MARL over Gaussian policy baselines.
FASTER models multi-candidate denoising as an MDP and trains a value function to filter actions early, delivering the performance of full sampling at lower cost in diffusion RL policies.
MeanFlow policies optimized by soft policy iteration with an average-divergence network and adaptive SNIS velocity estimation match diffusion RL performance at far lower sampling cost.
TRFP combines rectified flow models with truncation to support multimodal policies in MaxEnt RL while allowing fast one-step sampling and stable training.
DreamPolicy integrates an autoregressive diffusion world model with policy learning to produce a single scalable policy that generalizes to unseen composite terrains for humanoid locomotion.
COLSON applies diffusion models to reinforcement learning for social robot navigation and adds controllability mechanisms that enable zero-shot adaptation to unseen static obstacles and altered objectives.
DPPO fine-tunes diffusion policies via policy gradients and outperforms prior RL approaches for diffusion policies and PG-tuned alternatives on robot benchmarks while enabling stable training and hardware deployment.
Stochastic MeanFlow Policies enable one-step generative control in off-policy mirror descent by mapping noise through a MeanFlow transform, yielding tractable entropy and improved MuJoCo performance over Gaussian and generative baselines.
Unsupervised behavioral mode discovery combined with mutual information rewards enables RL fine-tuning of multimodal generative policies that achieves higher success rates without losing action diversity.
D2AC combines a diffusion actor with a distributional critic via fused distributional RL and clipped double Q-learning to reach state-of-the-art results on 18 hard control benchmarks including Humanoid, Dog, and Shadow Hand.
SDPG is a new on-policy visual RL algorithm that estimates gradients via stochastic perturbations of rollouts, achieving faster training and lower memory use than baselines on visual MuJoCo tasks while adding new robotics benchmarks and sim-to-real results.
citing papers explorer
-
Expressivity and Statistical Trade-offs in Diffusion Policy Learning
Drift Lipschitz budget K yields 1/K value approximation for diffusion policies, with matching lower bound, and finite-sample rates Õ(n^{-2/(m+6)}) (generic) or Õ(n^{-2/(m+4)}) (dissipative).
-
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.
-
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.
-
Aligning Flow Map Policies with Optimal Q-Guidance
Flow map policies enable fast one-step inference for flow-based RL policies, and FMQ provides an optimal closed-form Q-guided target for offline-to-online adaptation under trust-region constraints, achieving SOTA performance.
-
Learning Hybrid-Control Policies for High-Precision In-Contact Manipulation Under Uncertainty
MATCH trains hybrid position-force RL policies that achieve up to 10% higher success rates and 5x fewer breaks than pose-only policies in fragile peg-in-hole tasks under localization uncertainty, with strong sim-to-real results.
-
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.
-
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.
-
Reversal Q-Learning
Reversal Q-Learning (RQL) proposes reversing flows for virtual trajectories and bias-variance reduction in an expanded MDP to train flow policies, reporting best average performance on 50 simulated robotic tasks versus prior flow-based offline RL methods.
-
Q-VGM: Q-Value-Gradient Matching for Off-Policy Reinforcement Learning of Flow-Matching VLA
Q-VGM offline RL fine-tuning converts critic Q-gradients into residual velocity targets for flow-matching VLAs, raising LIBERO success from 75.0% to 92.5%.
-
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.
-
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.
-
Score-Based One-step MeanFlow Policy Optimization
SOM is an actor-critic algorithm that constructs the target velocity field for one-step MeanFlow policies directly from the Q-function via score estimation and probability flow ODE, achieving claimed SOTA on locomotion tasks with reduced training and inference time.
-
Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing
Recasts sampling-based nonconvex optimization as smoothed gradient descent to obtain non-asymptotic convergence guarantees and introduces the DIDA annealed algorithm that converges to the global optimum.
-
Decentralized Diffusion Policy Learning for Enhanced Exploration in Cooperative Multi-agent Reinforcement Learning
Decentralized diffusion policies trained with importance sampling score matching enhance exploration and performance in cooperative MARL over Gaussian policy baselines.
-
FASTER: Value-Guided Sampling for Fast RL
FASTER models multi-candidate denoising as an MDP and trains a value function to filter actions early, delivering the performance of full sampling at lower cost in diffusion RL policies.
-
Mean Flow Policy Optimization
MeanFlow policies optimized by soft policy iteration with an average-divergence network and adaptive SNIS velocity estimation match diffusion RL performance at far lower sampling cost.
-
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.
-
DreamPolicy: A Unified World-model Policy for Scalable Humanoid Locomotion
DreamPolicy integrates an autoregressive diffusion world model with policy learning to produce a single scalable policy that generalizes to unseen composite terrains for humanoid locomotion.
-
COLSON: Controllable Learning-Based Social Navigation via Diffusion-Based Reinforcement Learning
COLSON applies diffusion models to reinforcement learning for social robot navigation and adds controllability mechanisms that enable zero-shot adaptation to unseen static obstacles and altered objectives.
-
Diffusion Policy Policy Optimization
DPPO fine-tunes diffusion policies via policy gradients and outperforms prior RL approaches for diffusion policies and PG-tuned alternatives on robot benchmarks while enabling stable training and hardware deployment.
-
Stochastic MeanFlow Policies: One-Step Generative Control with Entropic Mirror Descent
Stochastic MeanFlow Policies enable one-step generative control in off-policy mirror descent by mapping noise through a MeanFlow transform, yielding tractable entropy and improved MuJoCo performance over Gaussian and generative baselines.
-
Behavioral Mode Discovery for Fine-tuning Multimodal Generative Policies
Unsupervised behavioral mode discovery combined with mutual information rewards enables RL fine-tuning of multimodal generative policies that achieves higher success rates without losing action diversity.
-
D2 Actor Critic: Diffusion Actor Meets Distributional Critic
D2AC combines a diffusion actor with a distributional critic via fused distributional RL and clipped double Q-learning to reach state-of-the-art results on 18 hard control benchmarks including Humanoid, Dog, and Shadow Hand.
-
Efficient On-policy Visual-RL via Stochastic Decoupled Policy Gradient
SDPG is a new on-policy visual RL algorithm that estimates gradients via stochastic perturbations of rollouts, achieving faster training and lower memory use than baselines on visual MuJoCo tasks while adding new robotics benchmarks and sim-to-real results.
- EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models