Efficient Planning with Latent Diffusion
- URL: http://arxiv.org/abs/2310.00311v1
- Date: Sat, 30 Sep 2023 08:50:49 GMT
- Title: Efficient Planning with Latent Diffusion
- Authors: Wenhao Li
- Abstract summary: Temporal abstraction and efficient planning pose significant challenges in offline reinforcement learning.
Latent action spaces offer a more flexible paradigm, capturing only possible actions within the behavior policy support.
This paper presents a unified framework for continuous latent action space representation learning and planning by leveraging latent, score-based diffusion models.
- Score: 18.678459478837976
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Temporal abstraction and efficient planning pose significant challenges in
offline reinforcement learning, mainly when dealing with domains that involve
temporally extended tasks and delayed sparse rewards. Existing methods
typically plan in the raw action space and can be inefficient and inflexible.
Latent action spaces offer a more flexible paradigm, capturing only possible
actions within the behavior policy support and decoupling the temporal
structure between planning and modeling. However, current latent-action-based
methods are limited to discrete spaces and require expensive planning. This
paper presents a unified framework for continuous latent action space
representation learning and planning by leveraging latent, score-based
diffusion models. We establish the theoretical equivalence between planning in
the latent action space and energy-guided sampling with a pretrained diffusion
model and incorporate a novel sequence-level exact sampling method. Our
proposed method, $\texttt{LatentDiffuser}$, demonstrates competitive
performance on low-dimensional locomotion control tasks and surpasses existing
methods in higher-dimensional tasks.
Related papers
- Diffusion Predictive Control with Constraints [51.91057765703533]
Diffusion predictive control with constraints (DPCC)
An algorithm for diffusion-based control with explicit state and action constraints that can deviate from those in the training data.
We show through simulations of a robot manipulator that DPCC outperforms existing methods in satisfying novel test-time constraints while maintaining performance on the learned control task.
arXiv Detail & Related papers (2024-12-12T15:10:22Z) - Action Mapping for Reinforcement Learning in Continuous Environments with Constraints [4.521631014571241]
We propose a novel DRL training strategy utilizing action mapping to streamline the learning process.
We demonstrate through experiments that action mapping significantly improves training performance in constrained environments.
arXiv Detail & Related papers (2024-12-05T16:42:45Z) - Adaptive Planning with Generative Models under Uncertainty [20.922248169620783]
Planning with generative models has emerged as an effective decision-making paradigm across a wide range of domains.
While continuous replanning at each timestep might seem intuitive because it allows decisions to be made based on the most recent environmental observations, it results in substantial computational challenges.
Our work addresses this challenge by introducing a simple adaptive planning policy that leverages the generative model's ability to predict long-horizon state trajectories.
arXiv Detail & Related papers (2024-08-02T18:07:53Z) - Simple Hierarchical Planning with Diffusion [54.48129192534653]
Diffusion-based generative methods have proven effective in modeling trajectories with offline datasets.
We introduce the Hierarchical diffuser, a 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.
arXiv Detail & Related papers (2024-01-05T05:28:40Z) - Unified Task and Motion Planning using Object-centric Abstractions of
Motion Constraints [56.283944756315066]
We propose an alternative TAMP approach that unifies task and motion planning into a single search.
Our approach is based on an object-centric abstraction of motion constraints that permits leveraging the computational efficiency of off-the-shelf AI search to yield physically feasible plans.
arXiv Detail & Related papers (2023-12-29T14:00:20Z) - Diffused Task-Agnostic Milestone Planner [13.042155799536657]
We propose a method to utilize a diffusion-based generative sequence model to plan a series of milestones in a latent space.
The proposed method can learn control-relevant, low-dimensional latent representations of milestones, which makes it possible to efficiently perform long-term planning and vision-based control.
arXiv Detail & Related papers (2023-12-06T10:09:22Z) - Planning as In-Painting: A Diffusion-Based Embodied Task Planning
Framework for Environments under Uncertainty [56.30846158280031]
Task planning for embodied AI has been one of the most challenging problems.
We propose a task-agnostic method named 'planning as in-painting'
The proposed framework achieves promising performances in various embodied AI tasks.
arXiv Detail & Related papers (2023-12-02T10:07:17Z) - AI planning in the imagination: High-level planning on learned abstract
search spaces [68.75684174531962]
We propose a new method, called PiZero, that gives an agent the ability to plan in an abstract search space that the agent learns during training.
We evaluate our method on multiple domains, including the traveling salesman problem, Sokoban, 2048, the facility location problem, and Pacman.
arXiv Detail & Related papers (2023-08-16T22:47:16Z) - Leveraging Scene Embeddings for Gradient-Based Motion Planning in Latent
Space [24.95320093765214]
AMP-LS is able to plan in novel, complex scenes while outperforming traditional planning baselines in terms of speed by an order of magnitude.
We show that the resulting system is fast enough to enable closed-loop planning in real-world dynamic scenes.
arXiv Detail & Related papers (2023-03-06T18:49:39Z) - Planning with Diffusion for Flexible Behavior Synthesis [125.24438991142573]
We consider what it would look like to fold as much of the trajectory optimization pipeline as possible into the modeling problem.
The core of our technical approach lies in a diffusion probabilistic model that plans by iteratively denoising trajectories.
arXiv Detail & Related papers (2022-05-20T07:02:03Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.