An information-theoretic approach to curiosity-driven reinforcement learning

No abstract is available for this paper.

• Publication year

  2012

• Venue

  Theory in biosciences

• Publication date

  2012-07-12

• Fields of study

  Medicine, Computer Science

• Identifiers
  DOI 10.1007/s12064-011-0142-zPMID 22791268
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Information Theory of Decisions and Actions

  2011cited by this paper
• Learning in embodied action-perception loops through exploration

  2011cited by this paper
• Dynamic policy programming

  2010cited by this paper
• Relative Entropy Policy Search

  2010cited by this paper
• Science as By-Products of Search for Novel Patterns , or Data Compressible in Unknown Yet Learnable Ways

  2009cited by this paper
• Efficient computation of optimal actions

  2009cited by this paper
• Transfer Learning for Reinforcement Learning Domains: A Survey

  2009cited by this paper
• Reinforcement learning of motor skills with policy gradients

  2008cited by this paper
• Multilayer in-place learning networks for modeling functional layers in the laminar cortex

  2008cited by this paper
• Predictive information and explorative behavior of autonomous robots

  2008influential reference
• On discovery and learning of models with predictive representations of state for agents with continuous actions and observations

  2007cited by this paper
• Information-theoretic approach to interactive learning

  2007cited by this paper
• Incremental Model-based Learners With Formal Learning-Time Guarantees

  2006cited by this paper
• A Mathematical Theory of Communication

  2006cited by this paper
• Intrinsically Motivated Reinforcement Learning

  2004cited by this paper
• How Many Clusters? An Information-Theoretic Perspective

  2003cited by this paper
• Geometric Clustering Using the Information Bottleneck Method

  2003cited by this paper
• Using MDP Characteristics to Guide Exploration in Reinforcement Learning

  2003cited by this paper
• Information Bottleneck for Gaussian Variables

  2003cited by this paper
• Covariant policy search

  2003cited by this paper
• Optimal Manifold Representation of Data: An Information Theoretic Approach

  2003cited by this paper
• Near-Optimal Reinforcement Learning in Polynomial Time

  2002cited by this paper
• R-MAX - A General Polynomial Time Algorithm for Near-Optimal Reinforcement Learning

  2001cited by this paper
• Regularities unseen, randomness observed: levels of entropy convergence.

  2001cited by this paper
• Synchronizing to the Environment: Information-Theoretic Constraints on Agent Learning

  2001cited by this paper
• The information bottleneck method

  2000cited by this paper
• Predictability, Complexity, and Learning

  2000cited by this paper
• Reinforcement Learning: An Introduction

  1998influential reference
• Deterministic annealing for clustering, compression, classification, regression, and related optimization problems

  1998cited by this paper
• Active Exploration in Dynamic Environments

  1991cited by this paper
• Curious model-building control systems

  1991cited by this paper
• Statistical mechanics and phase transitions in clustering.

  1990cited by this paper
• Learning from delayed rewards

  1989cited by this paper
• The Dripping Faucet As A Model Chaotic System

  1984cited by this paper
• Information Theory and Statistical Mechanics

  1957cited by this paper
• This article has been accepted for inclusion in a future issue of this journal. Content is final as presented, with the exception of pagination. IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION 1 Intrinsic Motivation Systems for Autonomous Mental Development

  year unknowncited by this paper

• Temporal Difference Learning with Constrained Initial Representations

  2026cites this paper
• Information-Theoretic Intrinsic Motivation for Reinforcement Learning in Combinatorial Routing.

  2026cites this paper
• IAPO: Information-Aware Policy Optimization for Token-Efficient Reasoning

  2026cites this paper
• Enhanced exploration in reinforcement learning using graph neural network based intrinsic reward mechanism

  2025cites this paper
• Modeling intrinsic motivation as reflective planning

  2025cites this paper
• Active Inference and Intentional Behavior

  2025cites this paper
• The World Is Bigger! A Computationally-Embedded Perspective on the Big World Hypothesis

  2025cites this paper
• Parameter Estimation using Reinforcement Learning Causal Curiosity: Limits and Challenges

  2025cites this paper
• Towards Human-Like Emergent Communication via Utility, Informativeness, and Complexity

  2025cites this paper
• Curiosity-Driven Exploration in Reinforcement Learning: An Adaptive Self-Supervised Learning Approach for Playing Action Games

  2025cites this paper
• Advanced deep reinforcement learning for optimizing 3D printing toolpaths: A framework with enhanced agent architectures, Count-Prioritized Replay, and curriculum learning

  2025cites this paper
• From pixels to planning: scale-free active inference

  2025cites this paper
• From Curiosity to Competence: How World Models Interact with the Dynamics of Exploration

  2025cites this paper
• Exploiting Policy Idling for Dexterous Manipulation

  2025cites this paper
• Leveraging Temporally Extended Behavior Sharing for Multi-task Reinforcement Learning

  2025cites this paper
• LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities

  2025cites this paper
• Sparse randomized policies for Markov decision processes based on Tsallis divergence regularization

  2024cites this paper
• Is Pessimism Provably Efficient for Offline Reinforcement Learning?

  2024cites this paper
• Proximal Policy Optimization with Adaptive Exploration

  2024cites this paper
• SURVIVAL IN A WORLD OF COMPLEX DANGERS.

  2024cites this paper
• Human decision making balances reward maximization and policy compression

  2024cites this paper
• Machine Learning With Computer Networks: Techniques, Datasets, and Models

  2024cites this paper
• Satisficing Exploration for Deep Reinforcement Learning

  2024cites this paper
• 'Snakes and ladders' in paleoanthropology: From cognitive surprise to skillfulness a million years ago.

  2024cites this paper
• Exploration and Anti-Exploration with Distributional Random Network Distillation

  2024cites this paper
• Learning to Assist Humans without Inferring Rewards

  2024cites this paper
• Efficient Variational Sequential Information Control

  2024cites this paper
• Wind Estimation in Unmanned Aerial Vehicles with Causal Machine Learning

  2024cites this paper
• Bayesian Reinforcement Learning With Limited Cognitive Load

  2023cites this paper
• Intrinsic Motivation via Surprise Memory

  2023cites this paper
• Federated inference and belief sharing

  2023cites this paper
• Beyond Surprise: Improving Exploration Through Surprise Novelty

  2023cites this paper
• Supervised structure learning

  2023cites this paper
• Curious Replay for Model-based Adaptation

  2023cites this paper
• Active sensing with predictive coding and uncertainty minimization

  2023cites this paper
• Active Inference and Intentional Behaviour

  2023cites this paper
• Reward Maximization Through Discrete Active Inference

  2023cites this paper
• Life-inspired Interoceptive Artificial Intelligence for Autonomous and Adaptive Agents

  2023cites this paper
• (Ir)rationality in AI: state of the art, research challenges and open questions

  2023cites this paper
• On the Appeal of Complexity

  2023cites this paper
• Extrinsic rewards, intrinsic rewards, and non-optimal behavior

  2022cites this paper
• Solving Dynamic Principal-Agent Problems with a Rationally Inattentive Principal

  2022cites this paper
• WILD-SCAV: Benchmarking FPS Gaming AI on Unity3D-based Environments

  2022cites this paper
• Path integrals, particular kinds, and strange things.

  2022cites this paper
• A Cooperation Graph Approach for Multiagent Sparse Reward Reinforcement Learning

  2022cites this paper
• Modeling Bounded Rationality in Multi-Agent Simulations Using Rationally Inattentive Reinforcement Learning

  2022cites this paper
• ICDVAE: An Effective Self-supervised Reinforcement Learning Method for behavior decisions of Non-player Characters in Metaverse Games

  2022cites this paper
• The free energy principle made simpler but not too simple

  2022cites this paper
• Self-Supervised Exploration via Temporal Inconsistency in Reinforcement Learning

  2022cites this paper
• Exploration in Deep Reinforcement Learning: A Survey

  2022cites this paper
• Guided self-organization through an entropy-based self-advising approach

  2022cites this paper
• MIT Open Access Articles Resource-rational decision making

  2022cites this paper
• Bibliometric Analysis of Information Theoretic Studies

  2022cites this paper
• Active inference, preference learning and adaptive behaviour

  2022cites this paper
• Trading off Utility, Informativeness, and Complexity in Emergent Communication

  2022cites this paper
• Curiously exploring affordance spaces of a pouring task

  2022cites this paper
• The free energy principle simplified 1 The free energy principle made simpler but not too simple

  2022cites this paper
• Spatial Consciousness Model of Intrinsic Reward in Partially Observable Environments

  2022cites this paper
• Designing ecosystems of intelligence from first principles

  2022cites this paper
• On Rate-Distortion Theory in Capacity-Limited Cognition & Reinforcement Learning

  2022cites this paper
• Rethinking statistical learning as a continuous dynamic stochastic process, from the motor systems perspective

  2022cites this paper
• Curiosity in hindsight

  2022cites this paper
• Five Properties of Specific Curiosity You Didn't Know Curious Machines Should Have

  2022cites this paper
• Complex behavior from intrinsic motivation to occupy future action-state path space

  2022cites this paper
• Explore and Control with Adversarial Surprise

  2021cites this paper
• Is Curiosity All You Need? On the Utility of Emergent Behaviours from Curious Exploration

  2021cites this paper
• Escaping Stochastic Traps with Aleatoric Mapping Agents

  2021influential citation
• Automatic HMI Structure Exploration Via Curiosity-Based Reinforcement Learning

  2021cites this paper
• A Drive towards Thermodynamic Efficiency for Dissipative Structures in Chemical Reaction Networks

  2021cites this paper
• SMiRL: Surprise Minimizing Reinforcement Learning in Unstable Environments

  2021cites this paper
• A Survey of Brain-Inspired Intelligent Robots: Integration of Vision, Decision, Motion Control, and Musculoskeletal Systems

  2021cites this paper
• Panta Rhei: Curiosity-Driven Exploration to Learn the Image-Schematic Affordances of Pouring Liquids

  2021cites this paper
• Improved Exploring Starts by Kernel Density Estimation-Based State-Space Coverage Acceleration in Reinforcement Learning

  2021cites this paper
• Active Inference: Demystified and Compared

  2021cites this paper
• Adapting Behaviour via Intrinsic Reward

  2021cites this paper
• Knowledge is reward: Learning optimal exploration by predictive reward cashing

  2021cites this paper
• Applications of the Free Energy Principle to Machine Learning and Neuroscience

  2021cites this paper
• Understanding the origin of information-seeking exploration in probabilistic objectives for control

  2021cites this paper
• Learning to Observe with Reinforcement Learning

  2021cites this paper
• How to Stay Curious while avoiding Noisy TVs using Aleatoric Uncertainty Estimation

  2021influential citation
• Extending the Capabilities of Reinforcement Learning Through Curriculum: A Review of Methods and Applications

  2021cites this paper
• Which Mutual-Information Representation Learning Objectives are Sufficient for Control?

  2021cites this paper
• World model learning and inference

  2021cites this paper
• Learn Goal-Conditioned Policy with Intrinsic Motivation for Deep Reinforcement Learning

  2021cites this paper
• Information is Power: Intrinsic Control via Information Capture

  2021cites this paper
• Exploration and preference satisfaction trade-off in reward-free learning

  2021cites this paper
• Policy compression: An information bottleneck in action selection

  2021cites this paper
• Combining Counterfactual Regret Minimization with Information Gain to Solve Extensive Games with Imperfect Information

  2021cites this paper
• Intrinsic Control of Variational Beliefs in Dynamic Partially-Observed Visual Environments

  2021cites this paper
• Combining Counterfactual Regret Minimization With Information Gain to Solve Extensive Games With Unknown Environments

  2021cites this paper
• Random curiosity-driven exploration in deep reinforcement learning

  2020cites this paper
• Adaptive Reward-Free Exploration

  2020cites this paper
• The relationship between dynamic programming and active inference: the discrete, finite-horizon case

  2020cites this paper
• Dynamic allocation of limited memory resources in reinforcement learning

  2020cites this paper
• Recent Developments Regarding Painting Robots for Research in Automatic Painting, Artificial Creativity, and Machine Learning

  2020cites this paper
• Mobile Robot Autonomous Environment Exploration Method based on Internal Motivation

  2020cites this paper
• Whence the Expected Free Energy?

  2020cites this paper
• Novelty Search in representational space for sample efficient exploration

  2020cites this paper
• Intrinsic Motivation Based Hierarchical Exploration for Model and Skill Learning

  2020cites this paper
• Origin of perseveration in the trade-off between reward and complexity

  2020cites this paper