Off-dynamics Conditional Diffusion Planners

• URL: http://arxiv.org/abs/2410.12238v1
• Date: Wed, 16 Oct 2024 04:56:43 GMT
• Title: Off-dynamics Conditional Diffusion Planners
• Authors: Wen Zheng Terence Ng, Jianda Chen, Tianwei Zhang,
• Abstract summary: This work explores the use of more readily available, albeit off-dynamics datasets, to address the challenge of data scarcity in Offline RL. We propose a novel approach using conditional Diffusion Probabilistic Models (DPMs) to learn the joint distribution of the large-scale off-dynamics dataset and the limited target dataset.
• Score: 15.321049697197447
• License:
• Abstract: Offline Reinforcement Learning (RL) offers an attractive alternative to interactive data acquisition by leveraging pre-existing datasets. However, its effectiveness hinges on the quantity and quality of the data samples. This work explores the use of more readily available, albeit off-dynamics datasets, to address the challenge of data scarcity in Offline RL. We propose a novel approach using conditional Diffusion Probabilistic Models (DPMs) to learn the joint distribution of the large-scale off-dynamics dataset and the limited target dataset. To enable the model to capture the underlying dynamics structure, we introduce two contexts for the conditional model: (1) a continuous dynamics score allows for partial overlap between trajectories from both datasets, providing the model with richer information; (2) an inverse-dynamics context guides the model to generate trajectories that adhere to the target environment's dynamic constraints. Empirical results demonstrate that our method significantly outperforms several strong baselines. Ablation studies further reveal the critical role of each dynamics context. Additionally, our model demonstrates that by modifying the context, we can interpolate between source and target dynamics, making it more robust to subtle shifts in the environment.

Related papers

• Synthetic location trajectory generation using categorical diffusion models [50.809683239937584]
  Diffusion models (DPMs) have rapidly evolved to be one of the predominant generative models for the simulation of synthetic data. We propose using DPMs for the generation of synthetic individual location trajectories (ILTs) which are sequences of variables representing physical locations visited by individuals.
  arXiv  Detail & Related papers  (2024-02-19T15:57:39Z)
• Federated Learning with Projected Trajectory Regularization [65.6266768678291]
  Federated learning enables joint training of machine learning models from distributed clients without sharing their local data. One key challenge in federated learning is to handle non-identically distributed data across the clients. We propose a novel federated learning framework with projected trajectory regularization (FedPTR) for tackling the data issue.
  arXiv  Detail & Related papers  (2023-12-22T02:12:08Z)
• Joint Distributional Learning via Cramer-Wold Distance [0.7614628596146602]
  We introduce the Cramer-Wold distance regularization, which can be computed in a closed-form, to facilitate joint distributional learning for high-dimensional datasets. We also introduce a two-step learning method to enable flexible prior modeling and improve the alignment between the aggregated posterior and the prior distribution.
  arXiv  Detail & Related papers  (2023-10-25T05:24:23Z)
• Amortized Network Intervention to Steer the Excitatory Point Processes [8.15558505134853]
  Excitatory point processes (i.e., event flows) occurring over dynamic graphs provide a fine-grained model to capture how discrete events may spread over time and space. How to effectively steer the event flows by modifying the dynamic graph structures presents an interesting problem, motivated by curbing the spread of infectious diseases. We design an Amortized Network Interventions framework, allowing for the pooling of optimal policies from history and other contexts.
  arXiv  Detail & Related papers  (2023-10-06T11:17:28Z)
• Learning Latent Dynamics via Invariant Decomposition and (Spatio-)Temporal Transformers [0.6767885381740952]
  We propose a method for learning dynamical systems from high-dimensional empirical data. We focus on the setting in which data are available from multiple different instances of a system. We study behaviour through simple theoretical analyses and extensive experiments on synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2023-06-21T07:52:07Z)
• Dynamic Latent Separation for Deep Learning [67.62190501599176]
  A core problem in machine learning is to learn expressive latent variables for model prediction on complex data. Here, we develop an approach that improves expressiveness, provides partial interpretation, and is not restricted to specific applications.
  arXiv  Detail & Related papers  (2022-10-07T17:56:53Z)
• Learning Sequential Latent Variable Models from Multimodal Time Series Data [6.107812768939553]
  We present a self-supervised generative modelling framework to jointly learn a probabilistic latent state representation of multimodal data. We demonstrate that our approach leads to significant improvements in prediction and representation quality.
  arXiv  Detail & Related papers  (2022-04-21T21:59:24Z)
• Learning to Continuously Optimize Wireless Resource in a Dynamic Environment: A Bilevel Optimization Perspective [52.497514255040514]
  This work develops a new approach that enables data-driven methods to continuously learn and optimize resource allocation strategies in a dynamic environment. We propose to build the notion of continual learning into wireless system design, so that the learning model can incrementally adapt to the new episodes. Our design is based on a novel bilevel optimization formulation which ensures certain fairness" across different data samples.
  arXiv  Detail & Related papers  (2021-05-03T07:23:39Z)
• Autoregressive Dynamics Models for Offline Policy Evaluation and Optimization [60.73540999409032]
  We show that expressive autoregressive dynamics models generate different dimensions of the next state and reward sequentially conditioned on previous dimensions. We also show that autoregressive dynamics models are useful for offline policy optimization by serving as a way to enrich the replay buffer.
  arXiv  Detail & Related papers  (2021-04-28T16:48:44Z)
• Explore the Context: Optimal Data Collection for Context-Conditional Dynamics Models [7.766117084613689]
  We learn dynamics models for parametrized families of dynamical systems with varying properties. We compute an action sequence which, for a limited number of environment interactions, optimally explores the given system. We demonstrate the effectiveness of our method for exploration on a non-linear toy-problem and two well-known reinforcement learning environments.
  arXiv  Detail & Related papers  (2021-02-22T22:52:39Z)
• Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning [124.9856253431878]
  We decompose the task of learning a global dynamics model into two stages: (a) learning a context latent vector that captures the local dynamics, then (b) predicting the next state conditioned on it. In order to encode dynamics-specific information into the context latent vector, we introduce a novel loss function that encourages the context latent vector to be useful for predicting both forward and backward dynamics. The proposed method achieves superior generalization ability across various simulated robotics and control tasks, compared to existing RL schemes.
  arXiv  Detail & Related papers  (2020-05-14T08:10:54Z)

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.