Parameterized Diffusion Policy learns a behavior manifold to condition diffusion policies on low-dimensional continuous parameters, enabling interpolation between strategies and adaptation to novel constraints without policy weight updates.
Policy-guided diffusion.arXiv preprint arXiv:2404.06356,
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative 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.
Advantage-guided diffusion (SAG and EAG) steers sampling in diffusion world models to higher-advantage trajectories, enabling policy improvement and better sample efficiency on MuJoCo tasks.
BiTrajDiff augments offline RL datasets by running independent forward and backward diffusion processes from intermediate states, yielding higher performance than prior one-directional data-augmentation baselines on D4RL.
ADWM is an offline evaluation method that uses a policy-guided latent diffusion world model to rank LLM agent policies from pre-collected trajectories, reporting positive Spearman correlations on four benchmarks.
CEDGE applies energy-guided trajectory diffusion to generate adapted samples for off-dynamics offline RL, improving planning and policy learning on the ODRL benchmark.
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.
DAWM introduces a modular diffusion world model with an inverse dynamics model to produce complete synthetic transitions that improve conservative offline RL algorithms like TD3BC and IQL on D4RL tasks.
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.
citing papers explorer
-
From Noise to Control: Parameterized Diffusion Policies
Parameterized Diffusion Policy learns a behavior manifold to condition diffusion policies on low-dimensional continuous parameters, enabling interpolation between strategies and adaptation to novel constraints without policy weight updates.
-
JEDI: Joint Embedding Diffusion World Model for Online Model-Based Reinforcement Learning
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.
-
Advantage-Guided Diffusion for Model-Based Reinforcement Learning
Advantage-guided diffusion (SAG and EAG) steers sampling in diffusion world models to higher-advantage trajectories, enabling policy improvement and better sample efficiency on MuJoCo tasks.
-
BiTrajDiff: Bidirectional Trajectory Generation with Diffusion Models for Offline Reinforcement Learning
BiTrajDiff augments offline RL datasets by running independent forward and backward diffusion processes from intermediate states, yielding higher performance than prior one-directional data-augmentation baselines on D4RL.
-
Autoregressive Diffusion World Models for Off-Policy Evaluation of LLM Agents
ADWM is an offline evaluation method that uses a policy-guided latent diffusion world model to rank LLM agent policies from pre-collected trajectories, reporting positive Spearman correlations on four benchmarks.
-
Cross-Domain Energy-Guided Diffusion Generation for Off-Dynamics Reinforcement Learning
CEDGE applies energy-guided trajectory diffusion to generate adapted samples for off-dynamics offline RL, improving planning and policy learning on the ODRL benchmark.
-
Refining Compositional Diffusion for Reliable Long-Horizon Planning
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.
-
DAWM: Diffusion Action World Models for Offline Reinforcement Learning via Action-Inferred Transitions
DAWM introduces a modular diffusion world model with an inverse dynamics model to produce complete synthetic transitions that improve conservative offline RL algorithms like TD3BC and IQL on D4RL tasks.
-
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.