REVIEW 6 cited by
Simple Hierarchical Planning with Diffusion
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
read the original abstract
Diffusion-based generative methods have proven effective in modeling trajectories with offline datasets. However, they often face computational challenges and can falter in generalization, especially in capturing temporal abstractions for long-horizon tasks. To overcome this, we introduce the Hierarchical Diffuser, a simple, fast, yet surprisingly effective planning method combining the advantages of hierarchical and diffusion-based planning. Our model adopts a "jumpy" planning strategy at the higher level, which allows it to have a larger receptive field but at a lower computational cost -- a crucial factor for diffusion-based planning methods, as we have empirically verified. Additionally, the jumpy sub-goals guide our low-level planner, facilitating a fine-tuning stage and further improving our approach's effectiveness. We conducted empirical evaluations on standard offline reinforcement learning benchmarks, demonstrating our method's superior performance and efficiency in terms of training and planning speed compared to the non-hierarchical Diffuser as well as other hierarchical planning methods. Moreover, we explore our model's generalization capability, particularly on how our method improves generalization capabilities on compositional out-of-distribution tasks.
Forward citations
Cited by 6 Pith papers
-
Reinforcement Learning for Flow-Matching Policies
Reward-weighted flow matching and GRPO with a learned reward surrogate both improve flow-matching policies beyond a suboptimal demonstrator on simulated unicycle tasks.
-
Hierarchical Reinforcement Learning with Uncertainty-Guided Diffusional Subgoals
HIDI trains a GP-regularized conditional diffusion model to generate high-level subgoals and mixes GP mean selection with diffusion sampling, outperforming HRL baselines on continuous control benchmarks.
-
Decision Flow Policy Optimization
Decision Flow frames the gradual action generation of flow-based policies as a flow MDP and updates the flow policy with flow-level value functions, reporting state-of-the-art results on several D4RL tasks.
-
Whole-Body Conditioned Egocentric Video Prediction
An autoregressive conditional diffusion transformer predicts future egocentric video from whole-body 3D pose sequences, trained on Nymeria, with atomic action and long-horizon evaluations.
-
Cascaded Diffusion Models for Neural Motion Planning
A cascaded diffusion planner with a coarse global model, a local refiner, and a one-shot collision-patching step improves success rates by roughly 3 to 5 percentage points over prior learned planners in simulated navi...
-
GenAI-based Multi-Agent Reinforcement Learning towards Distributed Agent Intelligence: A Generative-RL Agent Perspective
A position paper claiming that generative-AI agents that model and predict multi-agent dynamics will replace today's reactive MARL approaches.
Discussion (0). Sign in to comment.