All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Hypernca Growing Developmental Networks With Neural Cellular Automata**arXiv ID:** 2204.11674 **Authors:** Elias Najarro, Shyam Sudhakaran, Claire Glanois, Sebastian Risi **Published:** 2022-04-25T14:08:50Z **Abstract:** In contrast to deep reinforcement learning agents, biological neural networks are grown through a self-organized developmental process. Here we propose a new hypernetwork approach to grow artificial neural networks based on neural cellular automata (NCA). Inspired by self-organising systems and information-theoretic approaches to developmental...Votes: 0GitHub stars: 3
- Implicit Twotower Policies**arXiv ID:** 2208.01191 **Authors:** Yunfan Zhao, Qingkai Pan, Krzysztof Choromanski, Deepali Jain, Vikas Sindhwani **Published:** 2022-08-02T01:23:50Z **Abstract:** We present a new class of structured reinforcement learning policy-architectures, Implicit Two-Tower (ITT) policies, where the actions are chosen based on the attention scores of their learnable latent representations with those of the input states. By explicitly disentangling action from state processing in the policy stack, we...Votes: 0GitHub stars: 3
- Improving The Data Efficiency Of Multiobjective Qualitydiversity Through Gradient Assistance And Crowding Exploration**arXiv ID:** 2302.12668 **Authors:** Hannah Janmohamed, Thomas Pierrot, Antoine Cully **Published:** 2023-02-24T14:48:28Z **Abstract:** Quality-Diversity (QD) algorithms have recently gained traction as optimisation methods due to their effectiveness at escaping local optima and capability of generating wide-ranging and high-performing solutions. Recently, Multi-Objective MAP-Elites (MOME) extended the QD paradigm to the multi-objective setting by maintaining a Pareto front in each cell of a...Votes: 0GitHub stars: 3
- Internet Of Agentic Things Networked Ai Agents ForInternet of Agentic Things: Networked AI Agents for Closed-Loop IoT Orchestration - The paper introduces the Internet of Agentic Things (IoAT), an architectural framework that integrates agentic AI, IoT, cyber-physical systems, Physic...Votes: 0GitHub stars: 3
- IntersagethesecureandverifiableinteroperabilityproResearch paper: InterSAGE: The Secure and Verifiable Interoperability Protocol for An Internet of Agents.Votes: 0GitHub stars: 3
- Introducing Symmetries To Black Box Meta Reinforcement Learning**arXiv ID:** 2109.10781 **Authors:** Louis Kirsch, Sebastian Flennerhag, Hado van Hasselt, Abram Friesen, Junhyuk Oh, Yutian Chen **Published:** 2021-09-22T15:09:58Z **Abstract:** Meta reinforcement learning (RL) attempts to discover new RL algorithms automatically from environment interaction. In so-called black-box approaches, the policy and the learning algorithm are jointly represented by a single neural network. These methods are very flexible, but they tend to underperform in terms of ...Votes: 0GitHub stars: 3
- Katakomba Tools And Benchmarks For Datadriven Nethack**arXiv ID:** 2306.08772 **Authors:** Vladislav Kurenkov, Alexander Nikulin, Denis Tarasov, Sergey Kolesnikov **Published:** 2023-06-14T22:50:25Z **Abstract:** NetHack is known as the frontier of reinforcement learning research where learning-based methods still need to catch up to rule-based solutions. One of the promising directions for a breakthrough is using pre-collected datasets similar to recent developments in robotics, recommender systems, and more under the umbrella of offline reinf...Votes: 0GitHub stars: 3
- Know Your Agent Reconnaissance Driven Pentesting OSkill generated from arXiv paper 2607.19837: Know Your Agent: Reconnaissance-Driven Pentesting of AI AgentsVotes: 0GitHub stars: 3
- Lamarckian Platform Pushing The Boundaries Of Evolutionary Reinforcement Learning Towards Asynchronous Commercial Games**arXiv ID:** 2209.10055 **Authors:** Hui Bai, Ruimin Shen, Yue Lin, Botian Xu, Ran Cheng **Published:** 2022-09-21T00:55:55Z **Abstract:** Despite the emerging progress of integrating evolutionary computation into reinforcement learning, the absence of a high-performance platform endowing composability and massive parallelism causes non-trivial difficulties for research and applications related to asynchronous commercial games. Here we introduce Lamarckian - an open-source platform featuring...Votes: 0GitHub stars: 3
- Large Scale Study Of Curiosity Driven LearningSkill for AI agent capabilitiesVotes: 0GitHub stars: 3
- Learning And Improving Backgammon Strategy**arXiv ID:** 2504.02221 **Authors:** Gregory R. Galperin **Published:** 2025-04-03T02:27:22Z **Abstract:** A novel approach to learning is presented, combining features of on-line and off-line methods to achieve considerable performance in the task of learning a backgammon value function in a process that exploits the processing power of parallel supercomputers. The off-line methods comprise a set of techniques for parallelizing neural network training and $TD(λ)$ reinforcement learning; her...Votes: 0GitHub stars: 3
- Learning Controllable 3d Level Generators**arXiv ID:** 2206.13623 **Authors:** Zehua Jiang, Sam Earle, Michael Cerny Green, Julian Togelius **Published:** 2022-06-27T20:43:56Z **Abstract:** Procedural Content Generation via Reinforcement Learning (PCGRL) foregoes the need for large human-authored data-sets and allows agents to train explicitly on functional constraints, using computable, user-defined measures of quality instead of target output. We explore the application of PCGRL to 3D domains, in which content-generation tasks nat...Votes: 0GitHub stars: 3
- Learning Hippo Biologically Detailed Ca3Biologically detailed CA3 auto-associative memory model extending Hopfield/Marr with 10 populations, 47 compartments, 5 plasticity rules, and cholinergic modulation. Demonstrates multi-attractor dynamics absent from minimal baselines.Votes: 0GitHub stars: 3
- Learning Synthetic Environments For Reinforcement Learning With Evolution Strategies**arXiv ID:** 2101.09721 **Authors:** Fabio Ferreira, Thomas Nierhoff, Frank Hutter **Published:** 2021-01-24T14:16:13Z **Abstract:** This work explores learning agent-agnostic synthetic environments (SEs) for Reinforcement Learning. SEs act as a proxy for target environments and allow agents to be trained more efficiently than when directly trained on the target environment. We formulate this as a bi-level optimization problem and represent an SE as a neural network. By using Natural Evoluti...Votes: 0GitHub stars: 3
- Learning Values Across Many Orders Of Magnitude**arXiv ID:** 1602.07714 **Authors:** Hado van Hasselt, Arthur Guez, Matteo Hessel, Volodymyr Mnih, David Silver **Published:** 2016-02-24T21:14:52Z **Abstract:** Most learning algorithms are not invariant to the scale of the function that is being approximated. We propose to adaptively normalize the targets used in learning. This is useful in value-based reinforcement learning, where the magnitude of appropriate value approximations can change over time when we update the policy of behavior....Votes: 0GitHub stars: 3
- Lifetime Policy Reuse And The Importance Of Task Capacity**arXiv ID:** 2106.01741 **Authors:** David M. Bossens, Adam J. Sobey **Published:** 2021-06-03T10:42:49Z **Abstract:** A long-standing challenge in artificial intelligence is lifelong reinforcement learning, where learners are given many tasks in sequence and must transfer knowledge between tasks while avoiding catastrophic forgetting. Policy reuse and other multi-policy reinforcement learning techniques can learn multiple tasks but may generate many policies. This paper presents two novel c...Votes: 0GitHub stars: 3
- Limbomorphs Emergent Agent DynamicsMethodology for studying emergent lifelike patterns (Limbomorphs) in Gifbreeder systems that encode spatiotemporal fields through aesthetic selection, analyzing their species-specific reactions to perturbations and assessing whether they exhibit genuine goal-directed behavior or merely its appearance.Votes: 0GitHub stars: 3
- Living Harness Is An Interactive Agent EvolverLiving-Harness Is an Interactive-Agent EvolverVotes: 0GitHub stars: 3
- Llm Agent Economies Information LimitsPre-registered experiment on small economies of frontier LLM agents (Claude Opus 4.8), testing information-theoretic capacity regions for wealth growth under market coupling and mean-field residual attractor dynamics. Activation: LLM agent economies, information-theoretic capacity, mean-field dynamics, attractor dynamics, market coupling, multi-agent simulation, wealth growth.Votes: 0GitHub stars: 3
- Llm Agents Social Structure Latent ObjectivesStudies whether social structure (role, audience, relational context) changes what LLM agents express publicly, without explicit objectives in prompts. LLM agents will increasingly act in socially structured settings where what is advantageous or costly to say depends on social context. Activation: LLM agents, social structure, latent objectives, social context, agent communication, audience effects, role-based behavior.Votes: 0GitHub stars: 3
- Llm Symbolic Communication Multi AgentCommunicative Language Symbolism Routing (CLSR): a test-time framework where multiple LLM agents autonomously invent, evolve, and share compact Language Symbolism Frameworks (LSFs) for efficient multi-agent reasoning. A latent-free router adaptively selects and composes these symbolic languages per query, reducing token cost 3-6x vs standard CoT while maintaining accuracy. Includes information-theoretic lower bound on token cost. Activation: CLSR, language symbolism, multi-agent communication...Votes: 0GitHub stars: 3
- Llmoxie Agentic Scientific SoftwareInstitutional AI platform (LLMoxie) with three-tiered architecture supporting multi-cloud and on-premise inference, LiteLLM/MLflow control plane for authentication, budgeting, PII masking, and observability, and an application augmentation layer for AI coding agents in scientific software development. Activation: LLMoxie, scientific software, AI coding agent, LiteLLM, MLflow, multi-cloud, PII masking, institutional AI.Votes: 0GitHub stars: 3
- Llms Agentic Ai Systems Smart Grids Tutorial Architectures ApplicationsSkill derived from arXiv:2607.18147 - LLMs and Agentic AI Systems for Smart Grids: A Tutorial on Architectures and ApplicationsVotes: 0GitHub stars: 3
- Llms And Agentic Ai Systems For Smart Grids A TutoDerived from arXiv:2607.18147 - LLMs and Agentic AI Systems for Smart Grids: A Tutorial on Architectures and ApplicationsVotes: 0GitHub stars: 3
- Local Rl Alignment Engineering本地基座模型强化学习对齐工程实践 - 涵盖 RLHF/DPO/GRPO 算法选型、显存优化、框架选择、数据工程与全流程实施指南Votes: 0GitHub stars: 3
- Logact Agentic ReliabilityLogAct - enabling agentic reliability via shared logs. Deconstructed state machine architecture where agents play a shared log for reliable execution in production environments. Use for: agent reliability, shared log architectures, agentic state machines, production agent systems, async agent coordination. Activation: LogAct, agentic reliability, shared log agents, agent state machine, agent coordination logs.Votes: 0GitHub stars: 3
- Logact Enabling Agentic ReliabilityAgents are LLM-driven components that can mutate environments in powerful, arbitrary ways. Extracting guarantees for the execution of agents in produc... Activation: systems engineering, control systemsVotes: 0GitHub stars: 3
- Mada Rl Multi Agent Debate Aware Reinforcement LeaDerived from arXiv:2607.18006 - MADA-RL: Multi-Agent Debate-Aware Reinforcement Learning for Parameter-Efficient Reasoning in Compact ModelsVotes: 0GitHub stars: 3
- Market Driven Multi Agent AlignmentMarket-Driven Multi-Agent Alignment - Out-of-Money Reinforcement Learning using market-based mechanisms with sealed-bid auction for evaluation budget allocation... Activation: multi-agent alignment, market-driven RL, MAS optimization.Votes: 0GitHub stars: 3
- Marketbased Reinforcement Learning In Partially Observable Worlds**arXiv ID:** 0105025v1 **Authors:** Ivo Kwee, Marcus Hutter, Juergen Schmidhuber **Published:** 2001-05-15T19:07:28Z **Abstract:** Unlike traditional reinforcement learning (RL), market-based RL is in principle applicable to worlds described by partially observable Markov Decision Processes (POMDPs), where an agent needs to learn short-term memories of relevant previous events in order to execute optimal actions. Most previous work, however, has focused on reactive settings (MDPs) instead of...Votes: 0GitHub stars: 3
- Maximum Mutation Reinforcement Learning For Scalable Control**arXiv ID:** 2007.13690 **Authors:** Karush Suri, Xiao Qi Shi, Konstantinos N. Plataniotis, Yuri A. Lawryshyn **Published:** 2020-07-24T16:29:19Z **Abstract:** Advances in Reinforcement Learning (RL) have demonstrated data efficiency and optimal control over large state spaces at the cost of scalable performance. Genetic methods, on the other hand, provide scalability but depict hyperparameter sensitivity towards evolutionary operations. However, a combination of the two methods has recently...Votes: 0GitHub stars: 3
- Mcp Agentic Ipodwdm Network AutomationMCP-enabled agentic AI architecture for autonomous control of vendor-agnostic IPoDWDM networks. Demonstrates live end-to-end lifecycle multi-layer automation and closed-loop control using GNPy and telemetry, validated on a real testbed. Activation: MCP, agentic network automation, IPoDWDM, GNPy, multi-layer automation, closed-loop control, network lifecycle.Votes: 0GitHub stars: 3
- Mechanistic Attention Guidance Agent Memory RefinementSkill derived from arXiv:2607.17621 - Mechanistic Attention Guidance for Agent Memory RefinementVotes: 0GitHub stars: 3
- Mechanistic Attention Guidance For Agent Memory ReDerived from arXiv:2607.17621 - Mechanistic Attention Guidance for Agent Memory RefinementVotes: 0GitHub stars: 3
- MeldaprotocolformergingknowledgeacrossdistributedaResearch paper: MELD: A Protocol for Merging Knowledge Across Distributed Agentic Memories.Votes: 0GitHub stars: 3
- Memsecbench Tracking Agent Memory Poisoning From PMemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and RepairVotes: 0GitHub stars: 3
- Metabolic Multi Agent OptimizerMetabolic Multi-Agent Optimizer (MMAO) - bio-inspired optimization with endogenous resource allocation. Each agent carries internal energy with private-public metabolic loop. Fitness improvements converted to metabolic gains regulating sensing, search amplitude, branching, pruning, respawning. Parameter-light, self-calibrating. Use when: optimization without manual hyperparameter tuning, bio-inspired meta-heuristics, adaptive resource allocation in multi-agent systems.Votes: 0GitHub stars: 3
- Metalearning By The Baldwin Effect**arXiv ID:** 1806.07917 **Authors:** Chrisantha Thomas Fernando, Jakub Sygnowski, Simon Osindero, Jane Wang, Tom Schaul, Denis Teplyashin, Pablo Sprechmann, Alexander Pritzel, Andrei A. Rusu **Published:** 2018-06-06T08:39:03Z **Abstract:** The scope of the Baldwin effect was recently called into question by two papers that closely examined the seminal work of Hinton and Nowlan. To this date there has been no demonstration of its necessity in empirically challenging tasks. Here we show that ...Votes: 0GitHub stars: 3
- Mlgoperf An Ml Guided Inliner To Optimize Performance**arXiv ID:** 2207.08389 **Authors:** Amir H. Ashouri, Mostafa Elhoushi, Yuzhe Hua, Xiang Wang, Muhammad Asif Manzoor, Bryan Chan, Yaoqing Gao **Published:** 2022-07-18T05:47:29Z **Abstract:** For the past 25 years, we have witnessed an extensive application of Machine Learning to the Compiler space; the selection and the phase-ordering problem. However, limited works have been upstreamed into the state-of-the-art compilers, i.e., LLVM, to seamlessly integrate the former into the optimization...Votes: 0GitHub stars: 3
- Mmao A Metabolic Multi Agent Optimizer With EndogeDerived from arXiv:2606.28109 - MMAO: A Metabolic Multi-Agent Optimizer with Endogenous Resource Allocation for Continuous and Discrete OptimizationVotes: 0GitHub stars: 3
- Mmao Cls Metabolic Multi Agent Optimization For JoDerived from arXiv:2607.01539 - MMAO-Cls: Metabolic Multi-Agent Optimization for Joint Feature Selection and Classifier TuningVotes: 0GitHub stars: 3
- Mmao Dyn A Metabolic Multi Agent Optimizer For DynDerived from arXiv:2607.00846 - MMAO-Dyn: A Metabolic Multi-Agent Optimizer for Dynamic OptimizationVotes: 0GitHub stars: 3
- Modularity In Reinforcement Learning Via Algorithmic Independence In Credit Assignment**arXiv ID:** 2106.14993 **Authors:** Michael Chang, Sidhant Kaushik, Sergey Levine, Thomas L. Griffiths **Published:** 2021-06-28T21:29:13Z **Abstract:** Many transfer problems require re-using previously optimal decisions for solving new tasks, which suggests the need for learning algorithms that can modify the mechanisms for choosing certain actions independently of those for choosing others. However, there is currently no formalism nor theory for how to achieve this kind of modular credit...Votes: 0GitHub stars: 3
- Mpac Multi Principal Agent CoordinationResearch paper: MPAC - A Multi-Principal Agent Coordination Protocol for Interoperable Multi-Agent Collaboration. Extends MCP and A2A protocols for cross-organizational agent collaboration.Votes: 0GitHub stars: 3
- Multi Agent FormalizationSkill for AI agent capabilitiesVotes: 0GitHub stars: 3
- Multi Agent RecommendersDesign and implement multi-agent recommender systems (MAVRS) with LLM-powered architectures. Use when building video/content recommender systems, implementing multi-agent coordination for recommendations, or designing explainable recommendation pipelines. Based on arXiv:2604.02211 - Multi-Agent Video Recommenders: Evolution, Patterns, and Open Challenges (WSDM 2026).Votes: 0GitHub stars: 3
- Multi Agent Robotic Control With Onboard Vision LanguageMulti-Agent Robotic Control with Onboard Vision-Language Models. Vision Language Models (VLMs) and Vision Language Action (VLA) models have shown promise in robotic control. Yet, they face significant challenges regarding explainability, generalization, and compute... Activation: agent, multi-agent, safety, control, planningVotes: 0GitHub stars: 3
- Multi Agent System 5g Throughput Prediction Multi Operator Urban EnvironmentsSkill derived from arXiv:2607.16930 - A Multi-Agent System for 5G Throughput Prediction in Multi-Operator Urban EnvironmentsVotes: 0GitHub stars: 3
- Multi Goal Reinforcement Learning Challenging RoboSkill for AI agent capabilitiesVotes: 0GitHub stars: 3
- Multi Modal Multi Environment Machine Teaching Robust RewardHierarchical machine teaching algorithm for robust reward learning across multiple MDPs. Demonstrates comparisons impose stronger constraints than demonstrations in unlimited-data regime. Greedily selects informative environments then queries low-cost feedback. Activation: machine teaching, reward learning, inverse reinforcement learning, multi-environment, robust reward, feedback modalities.Votes: 0GitHub stars: 3