Inferential Induction: A Novel Framework for Bayesian Reinforcement Learning

• URL: http://arxiv.org/abs/2002.03098v2
• Date: Wed, 1 Jul 2020 19:16:51 GMT
• Title: Inferential Induction: A Novel Framework for Bayesian Reinforcement Learning
• Authors: Hannes Eriksson and Emilio Jorge and Christos Dimitrakakis and Debabrota Basu and Divya Grover
• Abstract summary: We describe a novel framework, Inferential Induction, for correctly inferring value function distributions from data. We experimentally demonstrate that the proposed algorithm is competitive with respect to the state of the art.
• Score: 6.16852156844376
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Bayesian reinforcement learning (BRL) offers a decision-theoretic solution for reinforcement learning. While "model-based" BRL algorithms have focused either on maintaining a posterior distribution on models or value functions and combining this with approximate dynamic programming or tree search, previous Bayesian "model-free" value function distribution approaches implicitly make strong assumptions or approximations. We describe a novel Bayesian framework, Inferential Induction, for correctly inferring value function distributions from data, which leads to the development of a new class of BRL algorithms. We design an algorithm, Bayesian Backwards Induction, with this framework. We experimentally demonstrate that the proposed algorithm is competitive with respect to the state of the art.

Related papers

• Reward-Directed Score-Based Diffusion Models via q-Learning [8.725446812770791]
  We propose a new reinforcement learning (RL) formulation for training continuous-time score-based diffusion models for generative AI. Our formulation does not involve any pretrained model for the unknown score functions of the noise-perturbed data distributions.
  arXiv  Detail & Related papers  (2024-09-07T13:55:45Z)
• Distributional Bellman Operators over Mean Embeddings [37.5480897544168]
  We propose a novel framework for distributional reinforcement learning, based on learning finite-dimensional mean embeddings of return distributions. We derive several new algorithms for dynamic programming and temporal-difference learning based on this framework.
  arXiv  Detail & Related papers  (2023-12-09T11:36:14Z)
• Value-Distributional Model-Based Reinforcement Learning [59.758009422067]
  Quantifying uncertainty about a policy's long-term performance is important to solve sequential decision-making tasks. We study the problem from a model-based Bayesian reinforcement learning perspective. We propose Epistemic Quantile-Regression (EQR), a model-based algorithm that learns a value distribution function.
  arXiv  Detail & Related papers  (2023-08-12T14:59:19Z)
• Provable Reward-Agnostic Preference-Based Reinforcement Learning [61.39541986848391]
  Preference-based Reinforcement Learning (PbRL) is a paradigm in which an RL agent learns to optimize a task using pair-wise preference-based feedback over trajectories. We propose a theoretical reward-agnostic PbRL framework where exploratory trajectories that enable accurate learning of hidden reward functions are acquired.
  arXiv  Detail & Related papers  (2023-05-29T15:00:09Z)
• Stochastic Unrolled Federated Learning [85.6993263983062]
  We introduce UnRolled Federated learning (SURF), a method that expands algorithm unrolling to federated learning. Our proposed method tackles two challenges of this expansion, namely the need to feed whole datasets to the unrolleds and the decentralized nature of federated learning.
  arXiv  Detail & Related papers  (2023-05-24T17:26:22Z)
• Classified as unknown: A novel Bayesian neural network [0.0]
  We develop a new efficient Bayesian learning algorithm for fully connected neural networks. We generalize the algorithm for a single perceptron for binary classification in citeH to multi-layer perceptrons for multi-class classification.
  arXiv  Detail & Related papers  (2023-01-31T04:27:09Z)
• STEERING: Stein Information Directed Exploration for Model-Based Reinforcement Learning [111.75423966239092]
  We propose an exploration incentive in terms of the integral probability metric (IPM) between a current estimate of the transition model and the unknown optimal. Based on KSD, we develop a novel algorithm algo: textbfSTEin information dirtextbfEcted exploration for model-based textbfReinforcement LearntextbfING.
  arXiv  Detail & Related papers  (2023-01-28T00:49:28Z)
• Bayesian Federated Neural Matching that Completes Full Information [2.6566593102111473]
  Federated learning is a machine learning paradigm where locally trained models are distilled into a global model. We propose a novel approach that overcomes this flaw by introducing a Kullback-Leibler divergence penalty at each iteration.
  arXiv  Detail & Related papers  (2022-11-15T09:47:56Z)
• Bayesian Bellman Operators [55.959376449737405]
  We introduce a novel perspective on Bayesian reinforcement learning (RL) Our framework is motivated by the insight that when bootstrapping is introduced, model-free approaches actually infer a posterior over Bellman operators, not value functions.
  arXiv  Detail & Related papers  (2021-06-09T12:20:46Z)
• Control as Hybrid Inference [62.997667081978825]
  We present an implementation of CHI which naturally mediates the balance between iterative and amortised inference. We verify the scalability of our algorithm on a continuous control benchmark, demonstrating that it outperforms strong model-free and model-based baselines.
  arXiv  Detail & Related papers  (2020-07-11T19:44:09Z)

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.