Conceptual Belief-Informed Reinforcement Learning

• URL: http://arxiv.org/abs/2410.01739v4
• Date: Sat, 08 Nov 2025 20:50:45 GMT
• Title: Conceptual Belief-Informed Reinforcement Learning
• Authors: Xingrui Gu, Chuyi Jiang, Laixi Shi,
• Abstract summary: Reinforcement learning (RL) has achieved significant success but is hindered by inefficiency and instability.<n>We introduce Conceptual Belief-Informed Reinforcement Learning to emulate human intelligence (HI-RL)<n>HI-RL forms concepts by extracting high-level categories of critical environmental information and then constructs adaptive concept-associated probabilistic beliefs as experience priors to guide value or policy updates.
• Score: 10.817700298999
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement learning (RL) has achieved significant success but is hindered by inefficiency and instability, relying on large amounts of trial-and-error data and failing to efficiently use past experiences to guide decisions. However, humans achieve remarkably efficient learning from experience, attributed to abstracting concepts and updating associated probabilistic beliefs by integrating both uncertainty and prior knowledge, as observed by cognitive science. Inspired by this, we introduce Conceptual Belief-Informed Reinforcement Learning to emulate human intelligence (HI-RL), an efficient experience utilization paradigm that can be directly integrated into existing RL frameworks. HI-RL forms concepts by extracting high-level categories of critical environmental information and then constructs adaptive concept-associated probabilistic beliefs as experience priors to guide value or policy updates. We evaluate HI-RL by integrating it into various existing value- and policy-based algorithms (DQN, PPO, SAC, and TD3) and demonstrate consistent improvements in sample efficiency and performance across both discrete and continuous control benchmarks.

Related papers

• ExGRPO: Learning to Reason from Experience [82.83309610498446]
  Reinforcement learning from verifiable rewards (RLVR) is an emerging paradigm for improving the reasoning ability of large language models.<n>Standard on-policy training discards rollout experiences after a single update, leading to computational inefficiency and instability.<n>In this paper, we are the first to investigate what makes a reasoning experience valuable and identify rollout correctness and entropy as effective indicators of experience value.
  arXiv  Detail & Related papers  (2025-10-02T17:31:30Z)
• Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models [47.05227816684691]
  We introduce a novel PSRL framework (AttnRL) which enables efficient exploration for reasoning models.<n>Motivated by preliminary observations that steps exhibiting high attention scores correlate with reasoning behaviors, we propose to branch from positions with high values.<n>We develop an adaptive sampling strategy that accounts for problem difficulty and historical batch size, ensuring that the whole training batch maintains non-zero advantage values.
  arXiv  Detail & Related papers  (2025-09-30T17:58:34Z)
• UserRL: Training Interactive User-Centric Agent via Reinforcement Learning [104.63494870852894]
  Reinforcement learning (RL) has shown promise in training agentic models that engage in dynamic, multi-turn interactions.<n>We propose UserRL, a unified framework for training and evaluating user-centric abilities through standardized gym environments.
  arXiv  Detail & Related papers  (2025-09-24T03:33:20Z)
• Unveiling the Learning Mind of Language Models: A Cognitive Framework and Empirical Study [50.065744358362345]
  Large language models (LLMs) have shown impressive capabilities across tasks such as mathematics, coding, and reasoning.<n>Yet their learning ability, which is crucial for adapting to dynamic environments and acquiring new knowledge, remains underexplored.
  arXiv  Detail & Related papers  (2025-06-16T13:24:50Z)
• Enhancing Rating-Based Reinforcement Learning to Effectively Leverage Feedback from Large Vision-Language Models [22.10168313140081]
  We introduce ERL-VLM, an enhanced rating-based reinforcement learning method that learns reward functions from AI feedback.<n>ERL-VLM queries large vision-language models for absolute ratings of individual trajectories, enabling more expressive feedback.<n>We demonstrate that ERL-VLM significantly outperforms existing VLM-based reward generation methods.
  arXiv  Detail & Related papers  (2025-06-15T12:05:08Z)
• Dynamic Programming Techniques for Enhancing Cognitive Representation in Knowledge Tracing [125.75923987618977]
  We propose the Cognitive Representation Dynamic Programming based Knowledge Tracing (CRDP-KT) model.<n>It is a dynamic programming algorithm to optimize cognitive representations based on the difficulty of the questions and the performance intervals between them.<n>It provides more accurate and systematic input features for subsequent model training, thereby minimizing distortion in the simulation of cognitive states.
  arXiv  Detail & Related papers  (2025-06-03T14:44:48Z)
• Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training [86.70255651945602]
  We introduce a novel inference-time steering methodology called Reinforcing Cognitive Experts (RICE)<n>RICE aims to improve reasoning performance without additional training or complexs.<n> Empirical evaluations with leading MoE-based LRMs demonstrate noticeable and consistent improvements in reasoning accuracy, cognitive efficiency, and cross-domain generalization.
  arXiv  Detail & Related papers  (2025-05-20T17:59:16Z)
• A Framework for Robust Cognitive Evaluation of LLMs [13.822169295436177]
  Emergent cognitive abilities in large language models (LLMs) have been widely observed, but their nature and underlying mechanisms remain poorly understood.<n>We develop CognitivEval, a framework for systematically evaluating the artificial cognitive capabilities of LLMs.
  arXiv  Detail & Related papers  (2025-04-03T17:35:54Z)
• Does "Reasoning" with Large Language Models Improve Recognizing, Generating, and Reframing Unhelpful Thoughts? [22.202600416432386]
  Cognitive Reframing helps individuals reinterpret negative experiences by finding positive meaning.<n>Recent advances in Large Language Models (LLMs) have demonstrated improved performance through reasoning-based strategies.<n>This inspires a promising direction of leveraging the reasoning capabilities of LLMs to improve CBT and mental reframing.
  arXiv  Detail & Related papers  (2025-03-31T19:19:34Z)
• How Metacognitive Architectures Remember Their Own Thoughts: A Systematic Review [16.35521789216079]
  We review how Computational Metacognitive Architectures (CMAs) model, store, remember and process their metacognitive experiences. We consider different aspects - ranging from the underlying psychological theories to the content and structure of collected data, to the algorithms used and evaluation results.
  arXiv  Detail & Related papers  (2025-02-28T08:48:41Z)
• Unveiling the Role of Expert Guidance: A Comparative Analysis of User-centered Imitation Learning and Traditional Reinforcement Learning [0.0]
  This study explores the performance, robustness, and limitations of imitation learning compared to traditional reinforcement learning methods. The insights gained from this study contribute to the advancement of human-centered artificial intelligence.
  arXiv  Detail & Related papers  (2024-10-28T18:07:44Z)
• Predicting and Understanding Human Action Decisions: Insights from Large Language Models and Cognitive Instance-Based Learning [0.0]
  Large Language Models (LLMs) have demonstrated their capabilities across various tasks. This paper exploits the reasoning and generative capabilities of the LLMs to predict human behavior in two sequential decision-making tasks. We compare the performance of LLMs with a cognitive instance-based learning model, which imitates human experiential decision-making.
  arXiv  Detail & Related papers  (2024-07-12T14:13:06Z)
• Balancing Rigor and Utility: Mitigating Cognitive Biases in Large Language Models for Multiple-Choice Questions [0.46873264197900916]
  This paper examines the role of cognitive biases in the decision-making processes of large language models (LLMs) We show that certain cognitive biases when properly balanced, can enhance decision-making efficiency through rational deviations and shortcuts.
  arXiv  Detail & Related papers  (2024-06-16T16:25:22Z)
• Brain-Inspired Continual Learning-Robust Feature Distillation and Re-Consolidation for Class Incremental Learning [0.0]
  We introduce a novel framework comprising two core concepts: feature distillation and re-consolidation. Our framework, named Robust Rehearsal, addresses the challenge of catastrophic forgetting inherent in continual learning systems. Experiments conducted on CIFAR10, CIFAR100, and real-world helicopter attitude datasets showcase the superior performance of CL models trained with Robust Rehearsal.
  arXiv  Detail & Related papers  (2024-04-22T21:30:11Z)
• A Unified and General Framework for Continual Learning [58.72671755989431]
  Continual Learning (CL) focuses on learning from dynamic and changing data distributions while retaining previously acquired knowledge. Various methods have been developed to address the challenge of catastrophic forgetting, including regularization-based, Bayesian-based, and memory-replay-based techniques. This research aims to bridge this gap by introducing a comprehensive and overarching framework that encompasses and reconciles these existing methodologies.
  arXiv  Detail & Related papers  (2024-03-20T02:21:44Z)
• Benchmarking Continual Learning from Cognitive Perspectives [14.867136605254975]
  Continual learning addresses the problem of continuously acquiring and transferring knowledge without catastrophic forgetting of old concepts. There is a mismatch between cognitive properties and evaluation methods of continual learning models. We propose to integrate model cognitive capacities and evaluation metrics into a unified evaluation paradigm.
  arXiv  Detail & Related papers  (2023-12-06T06:27:27Z)
• Variational Curriculum Reinforcement Learning for Unsupervised Discovery of Skills [25.326624139426514]
  We propose a novel approach to unsupervised skill discovery based on information theory, called Value Uncertainty Vari Curriculum Curriculum (VUVC) We prove that, under regularity conditions, VUVC accelerates the increase of entropy in the visited states compared to the uniform curriculum. We also demonstrate that the skills discovered by our method successfully complete a real-world robot navigation task in a zero-shot setup.
  arXiv  Detail & Related papers  (2023-10-30T10:34:25Z)
• Explaining by Imitating: Understanding Decisions by Interpretable Policy Learning [72.80902932543474]
  Understanding human behavior from observed data is critical for transparency and accountability in decision-making. Consider real-world settings such as healthcare, in which modeling a decision-maker's policy is challenging. We propose a data-driven representation of decision-making behavior that inheres transparency by design, accommodates partial observability, and operates completely offline.
  arXiv  Detail & Related papers  (2023-10-28T13:06:14Z)
• From Heuristic to Analytic: Cognitively Motivated Strategies for Coherent Physical Commonsense Reasoning [66.98861219674039]
  Heuristic-Analytic Reasoning (HAR) strategies drastically improve the coherence of rationalizations for model decisions. Our findings suggest that human-like reasoning strategies can effectively improve the coherence and reliability of PLM reasoning.
  arXiv  Detail & Related papers  (2023-10-24T19:46:04Z)
• A Study of Situational Reasoning for Traffic Understanding [63.45021731775964]
  We devise three novel text-based tasks for situational reasoning in the traffic domain. We adopt four knowledge-enhanced methods that have shown generalization capability across language reasoning tasks in prior work. We provide in-depth analyses of model performance on data partitions and examine model predictions categorically.
  arXiv  Detail & Related papers  (2023-06-05T01:01:12Z)
• OlaGPT: Empowering LLMs With Human-like Problem-Solving Abilities [19.83434949066066]
  This paper introduces a novel intelligent framework, referred to as OlaGPT. OlaGPT carefully studied a cognitive architecture framework, and propose to simulate certain aspects of human cognition. The framework involves approximating different cognitive modules, including attention, memory, reasoning, learning, and corresponding scheduling and decision-making mechanisms.
  arXiv  Detail & Related papers  (2023-05-23T09:36:51Z)
• Interpreting Neural Policies with Disentangled Tree Representations [58.769048492254555]
  We study interpretability of compact neural policies through the lens of disentangled representation. We leverage decision trees to obtain factors of variation for disentanglement in robot learning. We introduce interpretability metrics that measure disentanglement of learned neural dynamics.
  arXiv  Detail & Related papers  (2022-10-13T01:10:41Z)
• Flexible Attention-Based Multi-Policy Fusion for Efficient Deep Reinforcement Learning [78.31888150539258]
  Reinforcement learning (RL) agents have long sought to approach the efficiency of human learning. Prior studies in RL have incorporated external knowledge policies to help agents improve sample efficiency. We present Knowledge-Grounded RL (KGRL), an RL paradigm fusing multiple knowledge policies and aiming for human-like efficiency and flexibility.
  arXiv  Detail & Related papers  (2022-10-07T17:56:57Z)
• Anti-Retroactive Interference for Lifelong Learning [65.50683752919089]
  We design a paradigm for lifelong learning based on meta-learning and associative mechanism of the brain. It tackles the problem from two aspects: extracting knowledge and memorizing knowledge. It is theoretically analyzed that the proposed learning paradigm can make the models of different tasks converge to the same optimum.
  arXiv  Detail & Related papers  (2022-08-27T09:27:36Z)
• Modeling Human Behavior Part II -- Cognitive approaches and Uncertainty [0.0]
  In Part I, we discussed methods which generate a model of behavior from exploration of the system and feedback based on the exhibited behavior. In this work, we will continue the discussion from the perspective of methods which focus on the assumed cognitive abilities, limitations, and biases demonstrated in human reasoning.
  arXiv  Detail & Related papers  (2022-05-13T07:29:15Z)
• Autonomous Reinforcement Learning: Formalism and Benchmarking [106.25788536376007]
  Real-world embodied learning, such as that performed by humans and animals, is situated in a continual, non-episodic world. Common benchmark tasks in RL are episodic, with the environment resetting between trials to provide the agent with multiple attempts. This discrepancy presents a major challenge when attempting to take RL algorithms developed for episodic simulated environments and run them on real-world platforms.
  arXiv  Detail & Related papers  (2021-12-17T16:28:06Z)
• Balancing Value Underestimation and Overestimation with Realistic Actor-Critic [6.205681604290727]
  This paper introduces a novel model-free algorithm, Realistic Actor-Critic(RAC), which can be incorporated with any off-policy RL algorithms to improve sample efficiency. RAC employs Universal Value Function Approximators (UVFA) to simultaneously learn a policy family with the same neural network, each with different trade-offs between underestimation and overestimation. We evaluate RAC on the MuJoCo benchmark, achieving 10x sample efficiency and 25% performance improvement on the most challenging Humanoid environment compared to SAC.
  arXiv  Detail & Related papers  (2021-10-19T03:35:01Z)
• Backprop-Free Reinforcement Learning with Active Neural Generative Coding [84.11376568625353]
  We propose a computational framework for learning action-driven generative models without backpropagation of errors (backprop) in dynamic environments. We develop an intelligent agent that operates even with sparse rewards, drawing inspiration from the cognitive theory of planning as inference. The robust performance of our agent offers promising evidence that a backprop-free approach for neural inference and learning can drive goal-directed behavior.
  arXiv  Detail & Related papers  (2021-07-10T19:02:27Z)
• IQ-Learn: Inverse soft-Q Learning for Imitation [95.06031307730245]
  imitation learning from a small amount of expert data can be challenging in high-dimensional environments with complex dynamics. Behavioral cloning is a simple method that is widely used due to its simplicity of implementation and stable convergence. We introduce a method for dynamics-aware IL which avoids adversarial training by learning a single Q-function.
  arXiv  Detail & Related papers  (2021-06-23T03:43:10Z)
• A Competence-aware Curriculum for Visual Concepts Learning via Question Answering [95.35905804211698]
  We propose a competence-aware curriculum for visual concept learning in a question-answering manner. We design a neural-symbolic concept learner for learning the visual concepts and a multi-dimensional Item Response Theory (mIRT) model for guiding the learning process. Experimental results on CLEVR show that with a competence-aware curriculum, the proposed method achieves state-of-the-art performances.
  arXiv  Detail & Related papers  (2020-07-03T05:08:09Z)
• Reinforcement Learning through Active Inference [62.997667081978825]
  We show how ideas from active inference can augment traditional reinforcement learning approaches. We develop and implement a novel objective for decision making, which we term the free energy of the expected future. We demonstrate that the resulting algorithm successfully exploration and exploitation, simultaneously achieving robust performance on several challenging RL benchmarks with sparse, well-shaped, and no rewards.
  arXiv  Detail & Related papers  (2020-02-28T10:28:21Z)

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.