🎯 Reinforcement Learning - jobz · Scour

Behavior-Constrained Reinforcement Learning with Receding-Horizon Credit Assignment for High-Performance Control 💾Agent Memory

arxiv.org·4d

Markov Decision Processes: The Language of Reinforcement Learning 💾Agent Memory

medium.com·5d

Reinforcement Learning From Human Feedback (RLHF) in Large Language Models(LLMs) 🧠LLMs

pub.towardsai.net

·6d

Continual learning for AI agents 💾Agent Memory

blog.langchain.com·4d·Hacker News

Hierarchical Reinforcement Learning with Augmented Step-Level Transitions for LLM Agents 🌐World Models

arxiv.org·2d

Reinforcement Learning for LLM Post-Training: A Survey 🧠LLMs

arxiv.org·1d

QaRL: Rollout-Aligned Quantization-Aware RL for Fast and Stable Training under Training--Inference Mismatch ⚡Inference

arxiv.org·12h

Reinforcement Learning with LLM-Guided Action Spaces for Synthesizable Lead Optimization 🧠LLMs

arxiv.org·12h

Predictive Representations for Skill Transfer in Reinforcement Learning 💾Agent Memory

arxiv.org·1d

Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning 🧠LLMs

arxiv.org·12h

Reinforcement Learning with Reward Machines for Sleep Control in Mobile Networks 💾Agent Memory

arxiv.org·12h

Offline RL for Adaptive Policy Retrieval in Prior Authorization 💾Agent Memory

arxiv.org·2d

Aligning Agents via Planning: A Benchmark for Trajectory-Level Reward Modeling 💾Agent Memory

arxiv.org·12h

Target Policy Optimization 🌐World Models

arxiv.org·2d

PriPG-RL: Privileged Planner-Guided Reinforcement Learning for Partially Observable Systems with Anytime-Feasible MPC 💾Agent Memory

arxiv.org·12h

Thompson Sampling for Infinite-Horizon Discounted Decision Processes 🌐World Models

arxiv.org·1d

Value Mirror Descent for Reinforcement Learning 💾Agent Memory

arxiv.org·2d

Provable Multi-Task Reinforcement Learning: A Representation Learning Framework with Low Rank Rewards 🌐World Models

arxiv.org·3d

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning 🌐World Models

arxiv.org·1d

Vintix II: Decision Pre-Trained Transformer is a Scalable In-Context Reinforcement Learner 💾Agent Memory

arxiv.org·2d

Loading more...