{"total":23,"rows":[{"id":"2205.11275","title":"RL with KL penalties is better viewed as Bayesian inference","created":"2022-05-23","cited_by_count":135,"area":null},{"id":"2206.00761","title":"On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting","created":"2022-06-01","cited_by_count":82,"area":null},{"id":"2305.14343","title":"Video Prediction Models as Rewards for Reinforcement Learning","created":"2023-05-23","cited_by_count":78,"area":null},{"id":"2111.00876","title":"On the Expressivity of Markov Reward","created":"2021-11-01","cited_by_count":71,"area":null},{"id":"2104.05043","title":"Learn Goal-Conditioned Policy with Intrinsic Motivation for Deep Reinforcement Learning","created":"2021-04-11","cited_by_count":17,"area":null},{"id":"2103.12726","title":"Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning","created":"2021-03-23","cited_by_count":15,"area":null},{"id":"2103.17258","title":"Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning","created":"2021-03-31","cited_by_count":15,"area":null},{"id":"2110.12997","title":"Unsupervised Domain Adaptation with Dynamics-Aware Rewards in Reinforcement Learning","created":"2021-10-25","cited_by_count":15,"area":null},{"id":"2111.11107","title":"Branching Time Active Inference: the theory and its generality","created":"2021-11-22","cited_by_count":15,"area":null},{"id":"2103.06859","title":"Understanding the Origin of Information-Seeking Exploration in Probabilistic Objectives for Control","created":"2021-03-11","cited_by_count":10,"area":null},{"id":"2107.00140","title":"Applications of the Free Energy Principle to Machine Learning and Neuroscience","created":"2021-06-30","cited_by_count":9,"area":null},{"id":"2310.06253","title":"A Unified View on Solving Objective Mismatch in Model-Based Reinforcement Learning","created":"2023-10-10","cited_by_count":9,"area":null},{"id":"2205.10316","title":"Complex behavior from intrinsic motivation to occupy action-state path space","created":"2022-05-20","cited_by_count":7,"area":null},{"id":"2109.00541","title":"Active Inference and Epistemic Value in Graphical Models","created":"2021-09-01","cited_by_count":6,"area":null},{"id":"2102.09180","title":"A maximum entropy model of bounded rational decision-making with prior beliefs and market feedback","created":"2021-02-18","cited_by_count":5,"area":null},{"id":"2103.06123","title":"The whole brain architecture approach: Accelerating the development of artificial general intelligence by referring to the brain","created":"2021-03-06","cited_by_count":5,"area":null},{"id":"2304.05008","title":"Habits and goals in synergy: a variational Bayesian framework for behavior","created":"2023-04-11","cited_by_count":4,"area":null},{"id":"2306.08014","title":"Realising Synthetic Active Inference Agents, Part I: Epistemic Objectives and Graphical Specification Language","created":"2023-06-13","cited_by_count":4,"area":null},{"id":"2408.06542","title":"Value of Information and Reward Specification in Active Inference and POMDPs","created":"2024-08-13","cited_by_count":4,"area":null},{"id":"2411.07362","title":"Factorised Active Inference for Strategic Multi-Agent Interactions","created":"2024-11-11","cited_by_count":4,"area":null},{"id":"2106.02390","title":"Online reinforcement learning with sparse rewards through an active inference capsule","created":"2021-06-04","cited_by_count":3,"area":null},{"id":"2410.00258","title":"Possible Principles for Aligned Structure Learning Agents","created":"2024-09-30","cited_by_count":3,"area":null},{"id":"2302.01098","title":"A general Markov decision process formalism for action-state entropy-regularized reward maximization","created":"2023-02-02","cited_by_count":1,"area":null}],"next_cursor":null}