🎮 Reinforcement Learning - aibrain0x01 · Scour

Markov Decision Processes: The Language of Reinforcement Learning 🤖AI

medium.com·4d

Value Mirror Descent for Reinforcement Learning 🔥PyTorch

arxiv.org·2d

Value-Guidance MeanFlow for Offline Multi-Agent Reinforcement Learning 🔒Federated Learning

arxiv.org·8h

Multi-agent Reach-avoid MDP via Potential Games and Low-rank Policy Structure 🦾Robotics

arxiv.org·8h

Enhancing sample efficiency in reinforcement-learning-based flow control: replacing the critic with an adaptive reduced-order model 🎨Diffusion Models

arxiv.org·2d

Anticipatory Reinforcement Learning: From Generative Path-Laws to Distributional Value Functions 🧠Neuromorphic Computing

arxiv.org·3d

PriPG-RL: Privileged Planner-Guided Reinforcement Learning for Partially Observable Systems with Anytime-Feasible MPC ⚛️Quantum Computing

arxiv.org·8h

Adaptive Incentive Design with Regret Minimization ⚖️AI Ethics

arxiv.org·2d

Aligning Agents via Planning: A Benchmark for Trajectory-Level Reward Modeling ✨Generative AI

arxiv.org·8h

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning 🧠Neuromorphic Computing

arxiv.org·1d

Behavior-Constrained Reinforcement Learning with Receding-Horizon Credit Assignment for High-Performance Control 🛡️AI Safety

arxiv.org·4d

Reinforcement Learning with Reward Machines for Sleep Control in Mobile Networks 📱Edge AI

arxiv.org·8h

Predictive Representations for Skill Transfer in Reinforcement Learning 🧠Machine Learning

arxiv.org·1d

Reinforcement Learning from Human Feedback: A Statistical Perspective 📝LLMs

arxiv.org·4d

Offline RL for Adaptive Policy Retrieval in Prior Authorization 🧠Machine Learning

arxiv.org·2d

Target Policy Optimization 🧠Machine Learning

arxiv.org·2d

Provable Multi-Task Reinforcement Learning: A Representation Learning Framework with Low Rank Rewards 🔒Federated Learning

arxiv.org·3d

MARL-GPT: Foundation Model for Multi-Agent Reinforcement Learning 📝LLMs

arxiv.org·2d

Thompson Sampling for Infinite-Horizon Discounted Decision Processes 🎨Diffusion Models

arxiv.org·1d

MC-CPO: Mastery-Conditioned Constrained Policy Optimization 🔒Federated Learning

arxiv.org·3d

Loading more...