Diffusion Policy models robot actions as a conditional diffusion process, outperforming prior state-of-the-art methods by 46.9% on average across 12 manipulation tasks from four benchmarks.
hub
Diffusion policies as an expressive policy class for offline reinforcement learning
19 Pith papers cite this work. Polarity classification is still indexing.
19
Pith papers citing it
hub tools
representative citing papers
JEDI is the first online end-to-end latent diffusion world model that trains latents from denoising loss rather than reconstruction, achieving competitive Atari100k results with 43% less VRAM and over 3x faster sampling than pixel diffusion baselines.
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.
Muninn accelerates diffusion trajectory planners up to 4.6x by spending an uncertainty budget to decide when to cache denoiser outputs, preserving performance and certifying bounded deviation from full computation.
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.
DOSER detects OOD actions via diffusion-model denoising error and applies selective regularization based on predicted transitions, proving gamma-contraction with performance bounds and outperforming priors on offline RL benchmarks.
Drifting MPC produces a unique distribution over trajectories that trades off data support against optimality and enables efficient receding-horizon planning under unknown dynamics.
DIAL uses intent-conditioned CFG and multi-intent GRPO to expand and preserve diverse modes in continuous-action preference RL, lifting RFS to 9.14 and surpassing both prior best (8.5) and human demonstration (8.13).
The k-step policy gradient converges exponentially close to the optimal deterministic policy in restricted classes, achieving O(1/T) rates under smoothness assumptions without distribution mismatch factors.
RCD steers compositional diffusion sampling toward high-density coherent plans by combining reconstruction-error guidance with overlap consistency, outperforming prior methods on locomotion, manipulation, and pixel-based long-horizon tasks.
AdamO modifies Adam with an orthogonality correction to ensure the spectral radius of the TD update operator stays below one, providing a theoretical stability guarantee for offline 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.
Sobolev-trained diffusion policies using trajectories and feedback gains provide warm-starts that reduce trajectory optimization solving time by 2x to 20x while avoiding compounding errors.
Fisher Decorator refines flow policies in offline RL via a local transport map and Fisher-matrix quadratic approximation of the KL constraint, yielding controllable error near the optimum and SOTA benchmark results.
DDPO uses policy gradients on the denoising process to optimize diffusion models for arbitrary rewards like human feedback or compressibility.
IDQL generalizes IQL into an actor-critic framework and uses diffusion policies for robust policy extraction, outperforming prior offline RL methods.
A malicious agent in multi-agent LLM consensus systems can be trained via a surrogate world model and RL to reduce consensus rates and prolong disagreement more effectively than direct prompt attacks.
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.
citing papers explorer
-
Receding-Horizon Control via Drifting Models
Drifting MPC produces a unique distribution over trajectories that trades off data support against optimality and enables efficient receding-horizon planning under unknown dynamics.