🎮 Reinforcement Learning - laurynas · Scour

Reinforcement Learning for Scalable and Trustworthy Intelligent Systems ⚙Context engineering

Learning Equilibria in Coordination Games via Minorization-Maximization 🤝Multi-Agent Systems

MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning 🤝Multi-Agent Systems

Dynamic Skill Lifecycle Management for Agentic Reinforcement Learning ⚙Context engineering

ODRPO: Ordinal Decompositions of Discrete Rewards for Robust Policy Optimization 🎯Reranking

The Cancellation Hypothesis in Critic-Free RL: From Outcome Rewards to Token Credits 🎮Deterministic Simulation

ASH: Agents that Self-Hone via Embodied Learning ⚙Context engineering

Achieving $\epsilon^{-2}$ Sample Complexity for Single-Loop Actor-Critic under Minimal Assumptions 🤝Multi-Agent Systems

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training ⚙Context engineering

Quantum Advantage in Multi Agent Reinforcement Learning 🤝Multi-Agent Systems

Natural Policy Gradient as Doubly Smoothed Policy Iteration: A Bellman-Operator Framework 🔍AI Interpretability

Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling 🎯Reranking

Resolving Action Bottleneck: Agentic Reinforcement Learning Informed by Token-Level Energy ⚙Context engineering

AHD Agent: Agentic Reinforcement Learning for Automatic Heuristic Design ⚙Context engineering

Peng's Q($\lambda$) for Conservative Value Estimation in Offline Reinforcement Learning 🧪Property-based Testing

Learning Agentic Policy from Action Guidance ⚙Context engineering

MAPLE: Latent Multi-Agent Play for End-to-End Autonomous Driving 🤝Multi-Agent Systems

Matrix-Space Reinforcement Learning for Reusing Local Transition Geometry ⚙Context engineering

Discrete Flow Matching for Offline-to-Online Reinforcement Learning ⚙Context engineering

ChipMATE: Multi-Agent Training via Reinforcement Learning for Enhanced RTL Generation 🤝Multi-Agent Systems

Sign up or log in to see more results

Log in to enable infinite scrolling