A Structural Threshold in Decision Capacity Governs Collapse in Self-Play Reinforcement Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Kujur, Arahan
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence 91A05, 91A26, 68T05, 68T42 I.2.6; I.2.8; F.2.2
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

On the Fundamental Limitations of Decentralized Learnable Reward Shaping in Cooperative Multi-Agent Reinforcement Learning
by: Akella, Aditya
Published: (2025)

Coopetition-Gym v1: A Formally Grounded Platform for Mixed-Motive Multi-Agent Reinforcement Learning under Strategic Coopetition
by: Pant, Vik, et al.
Published: (2026)

Emotion-Inspired Learning Signals (EILS): A Homeostatic Framework for Adaptive Autonomous Agents
by: Tiwari, Dhruv
Published: (2025)

Memory-Augmented State Machine Prompting: A Novel LLM Agent Framework for Real-Time Strategy Games
by: Qi, Runnan, et al.
Published: (2025)

Adaptive Minds: Empowering Agents with LoRA-as-Tools
by: Shekar, Pavan C, et al.
Published: (2025)

Mastering NIM and Impartial Games with Weak Neural Networks: An AlphaZero-inspired Multi-Frame Approach
by: Riis, Søren
Published: (2024)

Resource-constrained Amazons chess decision framework integrating large language models and graph attention
by: Qian, Tianhao, et al.
Published: (2026)

Normalisation and Initialisation Strategies for Graph Neural Networks in Blockchain Anomaly Detection
by: Duy, Dang Sy, et al.
Published: (2026)

Computational Hardness of Reinforcement Learning with Partial $q^π$-Realizability
by: Karimi, Shayan, et al.
Published: (2025)

STRIDE: A Self-Reflective Agent Framework for Reliable Automatic Equation Discovery
by: Su, Jiarui, et al.
Published: (2026)

Diffusion-MPC in Discrete Domains: Feasibility Constraints, Horizon Effects, and Critic Alignment: Case study with Tetris
by: Wang, Haochuan Kevin
Published: (2026)

A Comparison Between Decision Transformers and Traditional Offline Reinforcement Learning Algorithms
by: Caunhye, Ali Murtaza, et al.
Published: (2025)

An Improved Adaptive PID Optimizer with Enhanced Convergence and Stability for Deep Learning
by: Saini, Saurabh, et al.
Published: (2026)

Emergent Coordination in Multi-Agent Systems via Pressure Fields and Temporal Decay
by: Rodriguez, Roland
Published: (2026)

Maximizing Rollout Informativeness under a Fixed Budget: A Submodular View of Tree Search for Tool-Use Agentic Reinforcement Learning
by: Hu, Yuelin, et al.
Published: (2026)

Generative Evolutionary Meta-Solver (GEMS): Scalable Surrogate-Free Multi-Agent Reinforcement Learning
by: Sharma, Alakh, et al.
Published: (2025)

Evolving machine learning workflows through interactive AutoML
by: Barbudo, Rafael, et al.
Published: (2024)

Generative World Models of Tasks: LLM-Driven Hierarchical Scaffolding for Embodied Agents
by: Hill, Brennen
Published: (2025)

Generating Realistic Safety-Critical Scenarios for Vehicle-Pedestrian Interactions
by: Pu, Qingwen, et al.
Published: (2026)

XAutoLM: Efficient Fine-Tuning of Language Models via Meta-Learning and AutoML
by: Estevanell-Valladares, Ernesto L., et al.
Published: (2025)

Connectivity-Aware Representations for Constrained Motion Planning via Multi-Scale Contrastive Learning
by: Jeon, Suhyun, et al.
Published: (2026)

Reinforcement Learning for Portfolio Optimization with a Financial Goal and Defined Time Horizons
by: Leukam, Fermat, et al.
Published: (2025)

SafeRL-Lite: A Lightweight, Explainable, and Constrained Reinforcement Learning Library
by: Mishra, Satyam, et al.
Published: (2025)

AI Agents: Evolution, Architecture, and Real-World Applications
by: Krishnan, Naveen
Published: (2025)

Mean-Field Reinforcement Learning without Synchrony
by: Yang, Shan
Published: (2026)

Law-Strength Frontiers and a No-Free-Lunch Result for Law-Seeking Reinforcement Learning on Volatility Law Manifolds
by: Zhang, Jian'an
Published: (2025)

Primal-Dual Sample Complexity Bounds for Constrained Markov Decision Processes with Multiple Constraints
by: Buckley, Max, et al.
Published: (2025)

LAWS: Learning from Actual Workloads Symbolically -- A Self-Certifying Parametrized Cache Architecture for Neural Inference, Robotics, and Edge Deployment
by: Magarshak, Gregory
Published: (2026)

The Axiom of Consent: Friction Dynamics in Multi-Agent Coordination
by: Farzulla, Murad
Published: (2026)

Risk-Sensitive Option Market Making with Arbitrage-Free eSSVI Surfaces: A Constrained RL and Stochastic Control Bridge
by: Zhang, Jian'an
Published: (2025)

Foundation Models as World Models: A Foundational Study in Text-Based GridWorlds
by: Sasso, Remo, et al.
Published: (2025)

Modeling and Controlling Deployment Reliability under Temporal Distribution Shift
by: Rahman, Naimur, et al.
Published: (2026)

Exploration with Foundation Models: Capabilities, Limitations, and Hybrid Approaches
by: Sasso, Remo, et al.
Published: (2025)

GoldenStart: Q-Guided Priors and Entropy Control for Distilling Flow Policies
by: Zhang, He, et al.
Published: (2026)

STACHE: Local Black-Box Explanations for Reinforcement Learning Policies
by: Elashkin, Andrew, et al.
Published: (2025)

OpCode-Based Malware Classification Using Machine Learning and Deep Learning Techniques
by: Saini, Varij, et al.
Published: (2025)

Optimistic Feasible Search for Closed-Loop Fair Threshold Decision-Making
by: Du, Wenzhang
Published: (2025)

Semantic-Constrained Federated Aggregation: Convergence Theory and Privacy-Utility Bounds for Knowledge-Enhanced Distributed Learning
by: Arafat, Jahidul
Published: (2025)

Tail-Safe Hedging: Explainable Risk-Sensitive Reinforcement Learning with a White-Box CBF--QP Safety Layer in Arbitrage-Free Markets
by: Zhang, Jian'an
Published: (2025)

Human Supervision as an Information Bottleneck: A Unified Theory of Error Floors in Human-Guided Learning
by: Dominguez, Alejandro Rodriguez
Published: (2026)