🎮 Reinforcement Learning - laurynas · Scour

LiSA: Lifelong Safety Adaptation via Conservative Policy Induction ⚙Context engineering

Gradient Extrapolation-Based Policy Optimization ⚙Context engineering

State-Centric Decision Process 🤝Multi-Agent Systems

Macro-Action Based Multi-Agent Instruction Following through Value Cancellation ⚙Context engineering

Learning and Reusing Policy Decompositions for Hierarchical Generalized Planning with LLM Agents ⚙Context engineering

Large Language Models for Agentic NetOps and AIOps: Architectures, Evaluation, and Safety 🤝Multi-Agent Systems

Offline Policy Optimization with Posterior Sampling ⚙Context engineering

Reward Hacking in Rubric-Based Reinforcement Learning 🧪Property-based Testing

When (and How) to Trust the Expert: Diagnosing Query-Time Expert-Guided Reinforcement Learning 🔍AI Interpretability

Adaptive Negative Reinforcement for LLM Reasoning:Dynamically Balancing Correction and Diversity in RLVR ⚙Context engineering

Multi-Objective Constraint Inference using Inverse reinforcement learning ⚙Context engineering

Learning Strategic Value and Cooperation in Multi-Player Stochastic Games through Side Payments 🤝Multi-Agent Systems

Beyond Reasoning: Reinforcement Learning Unlocks Parametric Knowledge in LLMs ⚙Context engineering

Learning What Matters: Adaptive Information-Theoretic Objectives for Robot Exploration 🔍AI Interpretability

Guided Streaming Stochastic Interpolant Policy 🔍AI Interpretability

Breaking $\textit{Winner-Takes-All}$: Cooperative Policy Optimization Improves Diverse LLM Reasoning ⚙Context engineering

MARLaaS: Multi-Tenant Asynchronous Reinforcement Learning as a Service ⚙Context engineering

Toward Modeling Player-Specific Chess Behaviors ⚙Context engineering

PIVOT: Bridging Planning and Execution in LLM Agents via Trajectory Refinement ⚙Context engineering

High-lift Wing Separation Control via Bayesian Optimization and Deep Reinforcement Learning 🔍AI Interpretability

No more posts from laurynas's subscribed feeds.

Scour all 25324 feeds Learn more about Feeds

Sign up or log in to see more results

Log in to enable infinite scrolling