Intrinsic Reward Methods

Follow this topic Ask about this topic

Intrinsic reward methods give agents feedback derived from their own experience or models, helping them explore when task rewards are sparse or absent. Common approaches reward novelty, prediction error, entropy, information gain, or empowerment; newer methods use confidence, self-evaluation, and learned rewards in language agents and robotics. These signals are used in settings from benchmark reinforcement learning and multi-agent coordination to reasoning and test-time policy improvement. A central challenge is that novelty and confidence can be misleading: rewards may favor irreducible noise or incorrect answers, and gains can collapse over training, so aligning internal signals with useful learning or task success remains an open problem.

Latest papers

30 papers3 papers in the last four weeks, down 25% on the four weeks before. 0.0% of all new papers.

Intrinsic Goals for Autonomous Agents: Hierarchical Exploration Captures Future Volitional Action in Drosophila
Oct 25, 2026Declan Kutscher, Reece Keller, Alyn Kirsch +2Intrinsic Motivation Intrinsic Reward Methods
Department of Computer Science, University of Maryland, College Park · Machine Learning Department, Carnegie Mellon University · Neuroscience Institute, Carnegie Mellon University +1
When Do Intrinsic Rewards Lead to Exploration?
Oct 1, 2026Scott W. Viteri, Laura Gomezjurado Gonzalez, Clark BarrettIntrinsic Reward Methods RL Exploration
Stanford University
Belief-Based Maximum Occupancy Principle and Active Inference
Sep 30, 2026Manolis Mylonas, Rubén Moreno BoteBelief-Space Planning Intrinsic Reward Methods
Center for Brain and Cognition & Department of Engineering Universitat Pompeu Fabra Barcelona, Spain
Intrinsic Motivation in Reinforcement Learning: A Research Agenda for Adaptive Self-Organisation
Sep 15, 2026Anatoly BelikovIntrinsic Motivation Intrinsic Reward Methods
SingularityNET Foundation
Intrinsic Robot Rewarding: Reusing VLA Representations for Autonomous Evaluation and Policy Improvement
Sep 15, 2026Tobias Schaffer, Mohab Elkhayat, Daniela Nicklas +2RL for Robotics Intrinsic Reward Methods
Technology Campus Cham - Intelligent Robotics, Deggendorf Institute of Technology, Cham, Germany
Efficient Exploration Is Enough
Sep 7, 2026Mikel Malagón, Jon Vadillo, Josu Ceberio +2Intrinsic Reward Methods RL Exploration
University of the Basque Country (UPV/EHU) · University of Alberta · Alberta Machine Intelligence Institute +2
Endogenous Exploration in Reinforcement Learning with Intrinsic Curiosity
Sep 4, 2026Armando VieiraRL Exploration Intrinsic Reward Methods
University of Tartu
PAST: Prompt-Adaptive Sampling Termination for Efficient Diffusion Model
Aug 7, 2026Renye Yan, Jikang Cheng, You Wu +4Intrinsic Reward Methods Reinforcement Learning
Peking University Beijing, China
Search-G1: Co-Evolving Representation-Based Rewards for Selective Grounded Search
Jul 24, 2026Ruoxi Cheng, Haoxuan Ma, Hongyi Zhang +7Retrieval-Augmented Generation LLM Grounding
Fudan University · Tencent · Nanjing University +2
Principled Direction-Free Intrinsic Motivation through Model-Free Epistemic Free-Energy Estimators
Jul 18, 2026Alireza Furutanpey, Schahram DustdarFree Energy Calculation Intrinsic Reward Methods
Coovally, Barcelona, Spain · Distributed Systems Group, TU Vienna, Austria · ICREA Barcelona, Spain
Trust Your Instincts: Confidence-Driven Test-Time RL for Vision-Language-Action Models
Jun 29, 2026Siyao Chen, Jiakang Yuan, Jiaxin Wang +1Intrinsic Reward Methods Reinforcement Learning
College of Future Information Technology, Fudan University, Shanghai, China · Shanghai Innovation Institute, Shanghai, China · MoShen Intelligence, Shanghai, China
OPERA: Aligning Open-Ended Reasoning via Objective Perplexity-based Reinforcement Learning
Jun 24, 2026Wenxuan Jiang, Zining Fan, Zijian Zhang +6Open-Ended Generation Intrinsic Reward Methods
The Hong Kong Polytechnic University · Peking University · Meituan Longcat Team +2
When Do Intrinsic Rewards Work for Code Reasoning? A Comprehensive Study
Jun 18, 2026Xiaolong Jin, Xuandong Zhao, Wenbo Guo +2RL for Code Generation Intrinsic Reward Methods
Purdue University · UC Berkeley · UC Santa Barbara
Can In-Context Learning Support Intrinsic Curiosity?
Jun 17, 2026Eric Elmoznino, Sangnie Bhardwaj, Johannes von Oswald +5Intrinsic Reward Methods Intrinsic Motivation
1Google – Paradigms of Intelligence Team, 2Google DeepMind
Momentum for Reasoning: Dense Intrinsic Signals in Policy Optimization
Jun 7, 2026Hao Chen, Zhanming Shen, Liyao Li +8Intrinsic Reward Methods Reinforcement Learning
Zhejiang University · The Chinese University of Hong Kong · Eastern Institute of Technology
Two is better than one: A Collapse-free Multi-Reward RLIF Training Framework
May 21, 2026Shourov Joarder, Diganta Sikdar, Ahsan Habib Akash +2KL-Regularized RL Intrinsic Reward Methods
Bangladesh University of Engineering and Technology, Bangladesh · West Virginia University, USA · University of Aberdeen, UK +2
CIG: Exploration via Conditional Information Gain
May 20, 2026Tim Joseph, Marcus Fechner, Philipp Stegmaier +2Intrinsic Reward Methods Intrinsic Motivation
FZI · KIT
Verifier-Free RL for LLMs via Intrinsic Gradient-Norm Reward
May 11, 2026Xuexiang Wen, Hang Yu, Linchao Zhu +1Intrinsic Reward Methods Reinforcement Learning
1Zhejiang University · 2Ant Group
Quality-Aware Exploration Budget Allocation for Cooperative Multi-Agent Reinforcement Learning
May 3, 2026Dahyun Oh, Minhyuk Yoon, H. Jin KimMulti-Agent Coordination Intrinsic Reward Methods
Department of Aerospace Engineering, Seoul National University, Seoul, Republic of Korea
MAGIC: Multi-Step Advantage-Gated Causal Influence for Multi-agent Reinforcement Learning
May 3, 2026Haohan Yu, Jinmiao Cong, Shengzhi Wang +2Multi-Agent Coordination Intrinsic Reward Methods
1Dalian University of Technology · 2Microsoft, Beijing, China
Curiosity-Critic: Cumulative Prediction Error Improvement as a Tractable Intrinsic Reward for World Model Training
Apr 20, 2026Vin Bhaskara, Haicheng WangIntrinsic Reward Methods Reinforcement Learning
Department of Computer Science, University of Toronto, Toronto, Canada.
Utilizing and Calibrating Hindsight Process Rewards via Reinforcement with Mutual Information Self-Evaluation
Apr 13, 2026Jiashu Yao, Heyan Huang, Zeming Liu +1Reinforcement Learning RL for LLM Agents
Beijing Institute of Technology · Beihang University
Co-Evolution of Policy and Internal Reward for Language Agents
Apr 3, 2026Xinyu Wang, Hanwei Wu, Jingwei Song +8RL for LLM Agents Intrinsic Reward Methods
McGill University · McMaster University · The University of Hong Kong +6
C-STEP: Continuous Space-Time Empowerment for Physics-informed Safe Reinforcement Learning of Mobile Agents
Mar 25, 2026Guihlerme Daubt, Adrian RedderSafe RL Safe Robot Navigation
Faculty of Technology, Bielefeld University, Germany · Department of Electrical Engineering and Information Technology, Paderborn University, Germany
Maximum-Entropy Exploration with Future State-Action Visitation Measures
Mar 19, 2026Adrien Bolland, Gaspard Lambrechts, Damien ErnstRL Exploration Intrinsic Reward Methods
University of Liège
When and Why Does Unsupervised RL Succeed in Mathematical Reasoning? A Manifold Envelopment Perspective
Mar 17, 2026Zelin Zhang, Fei Cheng, Chenhui ChuUnsupervised RL Reinforcement Learning
Kyoto University
How Far Can Unsupervised RLVR Scale LLM Training?
Mar 9, 2026Bingxiang He, Yuxin Zuo, Zeyuan Liu +18RL for Language Models Reinforcement Learning with Verifiable Rewards
Tsinghua University · Shanghai AI Lab · Xi’an Jiaotong University +3
Learning to Generate via Understanding: Understanding-Driven Intrinsic Rewarding for Unified Multimodal Models
Mar 6, 2026Jiadong Pan, Liang Li, Yuxin Peng +6Unified Multimodal Models T2I Generation
Institute of Computing Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Peking University +2
Adaptive Correlation-Weighted Intrinsic Rewards for Reinforcement Learning
Feb 27, 2026Viet Bac Nguyen, Phuong Thai NguyenIntrinsic Reward Methods Reward Design for RL
Institute for Artificial Intelligence, VNU-University of Engineering and Technology, Hanoi, Vietnam
ELEMENT: Episodic and Lifelong Exploration via Maximum Entropy
Dec 5, 2024Hongming Li, Zhao Yang, Xiaoxuan Liang +2Reward-Free RL Reinforcement Learning
Zhejiang Lab, Huangzhou, China · Vrije Universiteit Amsterdam, Amsterdam, the Netherlands · Computational NeuroEngineering Laboratory at the University of Florida, Gainesville, USA

Oct 25, 2026J/K move · Enter open · S save

Intrinsic Goals for Autonomous Agents: Hierarchical Exploration Captures Future Volitional Action in Drosophila

Declan Kutscher, Reece Keller, Alyn Kirsch, Felix Pei+1

Department of Computer Science, University of Maryland, College Park · Machine Learning Department, Carnegie Mellon University · Neuroscience Institute, Carnegie Mellon University+1

Intrinsic Motivation Intrinsic Reward Methods Agent Skill Learning Hierarchical RL Neural Encoding Behavioral Diversity in RL

Open paper AskPDF arXiv

Animals have a remarkable capacity for autonomy---driven by intrinsic motivation---without external sensory cues or extrinsic objectives, yet the computational mechanisms behind this ability largely remain a mystery. We combine whole-brain recordings in the fruit fly (Drosophila melanogaster), which reveal neural representations of spontaneous exploratory decisions more than 10 seconds in advance, with a neuromechanical digital twin to test whether optimizing intrinsic goals yields realistically embodied artificial agents that quantitatively match fly behavior and internal representations of future volitional action during exploration. Our hierarchical policy selects from a discrete library of low-level motor primitives, consistent with ethological theories of behavioral syllables. We train agents without external reward using 20 intrinsic motivation algorithms spanning curiosity, entropy, and competency methods. The agents are evaluated in a virtual tethered-ball assay modeled on the fly experiment, comparing spontaneous locomotor statistics and internal representations and decoding future turn direction from kinematics and neural activity on the same timescales observed in flies. DIAYN, a hierarchical competency algorithm learning discrete policies that maximize behavioral entropy and the separability of induced sensory observations, achieves the strongest joint behavioral and neural prospective coding performance relative to flies. Its learned policies closely capture individual variability in fly exploration strategies, suggesting that this diversity serves to maximize state-space coverage at the population level. DIAYN's latent activity also closely captures the sum-difference rule for interhemispheric encoding of kinematics in biological flies. These results establish hierarchical, intrinsically motivated agents as a powerful framework for reverse-engineering animal autonomy.