🎯 RLHF - ghosh.debasish · Scour

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

pub.towardsai.net

·6d

Predictive Representations for Skill Transfer in Reinforcement Learning 🤖AI Agents

arxiv.org·1d

Zero-Shot Alignment: Harm Detection via Incongruent Attention Mechanisms 🧠Reasoning Models

lesswrong.com·1d

Markov Decision Processes: The Language of Reinforcement Learning 🧠Reasoning Models

medium.com·4d

Three Ways Machines Learn 🧠Reasoning Models

medium.com·3d

Aligning Agents via Planning: A Benchmark for Trajectory-Level Reward Modeling 🧠Reasoning Models

arxiv.org·6h

ReflectRM: Boosting Generative Reward Models via Self-Reflection within a Unified Judgment Framework 🧠LLMs

arxiv.org·6h

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

arxiv.org·6h

Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization 🧠Reasoning Models

arxiv.org·1d

Active Reward Machine Inference From Raw State Trajectories 🧠Reasoning Models

arxiv.org·6h

Hierarchical Reinforcement Learning with Augmented Step-Level Transitions for LLM Agents 🧠LLMs

arxiv.org·2d

ViVa: A Video-Generative Value Model for Robot Reinforcement Learning 🧠Reasoning Models

arxiv.org·6h

Curr-RLCER:Curriculum Reinforcement Learning For Coherence Explainable Recommendation 🧠Reasoning Models

arxiv.org·2d

Reinforcement Learning from Human Feedback: A Statistical Perspective 🧠Reasoning Models

arxiv.org·4d

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

arxiv.org·6h

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning 🧠Reasoning Models

arxiv.org·1d

Beyond Stochastic Exploration: What Makes Training Data Valuable for Agentic Search 🤖AI Agents

arxiv.org·6h

Value-Guidance MeanFlow for Offline Multi-Agent Reinforcement Learning 🤖AI Agents

arxiv.org·6h

Cross-fitted Proximal Learning for Model-Based Reinforcement Learning 🧠Reasoning Models

arxiv.org·2d

Behavior-Constrained Reinforcement Learning with Receding-Horizon Credit Assignment for High-Performance Control 🤖AI Agents

arxiv.org·4d

Loading more...