paper-with-me

홈 › Papers

A Tractable Inference Perspective of Offline RL

2023-10-31 · Xuejie Liu, Anji Liu, Guy Van Den Broeck, Yitao Liang

A popular paradigm for offline Reinforcement Learning (RL) tasks is to first fit the offline trajectories to a sequence model, and then prompt the model for actions that lead to high expected return. In addition to obtaining accurate sequence models, this paper highlights that tractability, the ability to exactly and efficiently answer various probabilistic queries, plays an important role in offline RL. Specifically, due to the fundamental stochasticity from the offline data-collection policies and the environment dynamics, highly non-trivial conditional/constrained generation is required to elicit rewarding actions. it is still possible to approximate such queries, we observe that such crude estimates significantly undermine the benefits brought by expressive sequence models. To overcome this problem, this paper proposes Trifle (Tractable Inference for Offline RL), which leverages modern Tractable Probabilistic Models (TPMs) to bridge the gap between good sequence models and high expected returns at evaluation time. Empirically, Trifle achieves the most state-of-the-art scores in 9 Gym-MuJoCo benchmarks against strong baselines. Further, owing to its tractability, Trifle significantly outperforms prior approaches in stochastic environments and safe RL tasks (e.g. with action constraints) with minimum algorithmic modifications.

📄 PDF Abstract BibTeX arXiv:2311.00094

Code (0)

등록된 구현이 없습니다.

Tasks

MuJoCoOffline RLReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Amortizing intractable inference in diffusion models for vision, language, and control

2024-05-31 · Siddarth Venkatraman, Moksh Jain, Luca Scimeca, Minsu Kim 외

Diffusion models have emerged as effective distribution estimators in vision, language, and reinforcement learning, but their use as priors in downstream tasks poses an intractable posterior inference problem. This paper…

continuous-controlContinuous ControlDeep Reinforcement LearningImage Generation+4

SPQR: Controlling Q-ensemble Independence with Spiked Random Model for Reinforcement Learning

2024-01-06 · NeurIPS 2023 11 · Dohyeok Lee, Seungyub Han, Taehyun Cho, Jungwoo Lee

Alleviating overestimation bias is a critical challenge for deep reinforcement learning to achieve successful performance on more complex tasks or offline datasets containing out-of-distribution data. In order to overcom…

Deep Reinforcement LearningDiversityOffline RLQ-Learning+2

Tractability through Exchangeability: A New Perspective on Efficient Probabilistic Inference

2014-01-07 · Mathias Niepert, Guy Van Den Broeck

Exchangeability is a central notion in statistics and probability theory. The assumption that an infinite sequence of data points is exchangeable is at the core of Bayesian statistics. However, finite exchangeability as …

Normalizing Flow Regression for Bayesian Inference with Offline Likelihood Evaluations

2025-04-15 · Chengkun Li, Bobby Huggins, Petrus Mikkola, Luigi Acerbi

Bayesian inference with computationally expensive likelihood evaluations remains a significant challenge in many scientific domains. We propose normalizing flow regression (NFR), a novel offline inference method for appr…

Bayesian Inferenceregression

Hierarchical Latent Structure Learning through Online Inference

2026-03-19 · Ines Aitsahalia, Kiyohito Iigaya arxiv

Learning systems must balance generalization across experiences with discrimination of task-relevant details. Effective learning therefore requires representations that support both. Online latent-cause models support in…