🎮 Reinforcement Learning - laurynas · Scour

Button‑pushing explorers: How to grasp that AI agents can do amazing things while knowing nothing 🔍AI Interpretability

techxplore.com·3d

AIS: Adaptive Importance Sampling for Quantized RL 🔍AI Interpretability

Self-Supervised On-Policy Reinforcement Learning via Contrastive Proximal Policy Optimisation ⚙Context engineering

Parallelizing Counterfactual Regret Minimization ⚙Context engineering

Reward-Conditioned Reinforcement Learning ⚙Context engineering

Action-Conditioned Risk Gating for Safety-Critical Control under Partial Observability ⚙Context engineering

GAGPO: Generalized Advantage Grouped Policy Optimization ⚙Context engineering

Skill-R1: Agent Skill Evolution via Reinforcement Learning ⚙Context engineering

Critic-Driven Voronoi-Quantization for Distilling Deep RL Policies to Explainable Models ⚙Context engineering

Learning from Failures: Correction-Oriented Policy Optimization with Verifiable Rewards ⚙Context engineering

Improved Model-based Reinforcement Learning with Smooth Kernels ⚙Context engineering

Second-Order Actor-Critic Methods for Discounted MDPs via Policy Hessian Decomposition ⚙Context engineering

A Switching System Theory of Q-Learning with Linear Function Approximation 🤝Multi-Agent Systems

Ergodic Imitation for Adaptive Exploration around Demonstrations ⚙Context engineering

Submodular Multi-Agent Policy Learning for Online Distributed Task Allocation in Open Multi-Agent Systems 🤝Multi-Agent Systems

Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States ⚙Context engineering

Driving Intents Amplify Planning-Oriented Reinforcement Learning ⚙Context engineering

Reinforcement Learning Measurement Model ⚙Context engineering

Learning to Build the Environment: Self-Evolving Reasoning RL via Verifiable Environment Synthesis ⚙Context engineering

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

Log in to enable infinite scrolling