Research Papers

96 articles · Updated every 3 hours · View all reads

All Articles 119,236 Blog Posts 126,530 Tech Tutorials 30,575 Research Papers 23,724 News 17,332 ⚡ AI Lessons

ArXiv cs.AI 🎮 Reinforcement Learning 📄 Paper ⚡ AI Lesson 3d ago

Gimitest: A Comprehensive Tool for Testing Reinforcement Learning Policies

arXiv:2607.07029v1 Announce Type: cross Abstract: Reinforcement learning (RL) policies can be unsafe and vulnerable to attacks. Ensuring their reliability is of

ArXiv cs.AI 🎮 Reinforcement Learning 📄 Paper ⚡ AI Lesson 3d ago

RLVP: Penalize the Path, Reward the Outcome

arXiv:2607.07435v1 Announce Type: cross Abstract: Agents acting on our behalf in the real world (e.g. placing phone calls) must learn online from costly, often

ArXiv cs.AI 🎮 Reinforcement Learning 📄 Paper ⚡ AI Lesson 4d ago

Self-Review Reinforcement Learning (SRRL) with Cross-Episode Memory and Policy Distillation

arXiv:2607.05541v1 Announce Type: cross Abstract: Reinforcement Learning is commonly used to train large language models using environmental feedback. In applie

ArXiv cs.AI 🎮 Reinforcement Learning 📄 Paper ⚡ AI Lesson 5d ago

Ensemble Elastic DQN: A Step Dependent Ensemble Approach for Reducing Overestimation in Deep Value-Based Reinforcement Learning

arXiv:2506.05716v2 Announce Type: replace-cross Abstract: Deep Q-Networks (DQN) can suffer from overestimation bias because bootstrapped targets use a maximisat

ArXiv cs.AI 🎮 Reinforcement Learning 📄 Paper ⚡ AI Lesson 5d ago

The Three Regimes of Offline-to-Online Reinforcement Learning

arXiv:2510.01460v4 Announce Type: replace-cross Abstract: Offline-to-online reinforcement learning (RL) has emerged as a practical paradigm that leverages offli

ArXiv cs.AI 🎮 Reinforcement Learning 📄 Paper ⚡ AI Lesson 5d ago

Safe RLHF Beyond Expectation: Stochastic Dominance for Universal Spectral Risk Control

arXiv:2603.10938v2 Announce Type: replace-cross Abstract: Safe Reinforcement Learning from Human Feedback (RLHF) typically enforces safety through expected cost

ArXiv cs.AI 🎮 Reinforcement Learning 📄 Paper ⚡ AI Lesson 1w ago

Hierarchical Reinforcement Learning in StarCraft Micromanagement with Influence Maps and Cluster-based Scripts

arXiv:2606.30092v1 Announce Type: new Abstract: Real-time strategy (RTS) games present significant AI challenges, characterized by expansive state-action spaces

ArXiv cs.AI 🎮 Reinforcement Learning 📄 Paper ⚡ AI Lesson 1w ago

Tandem Reinforcement Learning with Verifiable Rewards

arXiv:2606.28166v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has significantly improved the reasoning capability of lar

ArXiv cs.AI 🎮 Reinforcement Learning 📄 Paper ⚡ AI Lesson 1w ago

Retroactive Advantage Correction: Closed-Form V-Trace Bias Correction for Delay-Aware RLHF

arXiv:2606.27580v1 Announce Type: cross Abstract: Reinforcement learning from human feedback (RLHF) in production does not always have a synchronous reward sign

ArXiv cs.AI 🎮 Reinforcement Learning 📄 Paper ⚡ AI Lesson 2w ago

Deterministic Pareto-Optimal Policy Synthesis for Multi-Objective Reinforcement Learning

arXiv:2606.26397v1 Announce Type: cross Abstract: Real-world decision-making often requires balancing multiple conflicting objectives, a challenge that standard

ArXiv cs.AI 🎮 Reinforcement Learning 📄 Paper ⚡ AI Lesson 2w ago

Auto-exploration for online reinforcement learning

arXiv:2512.06244v2 Announce Type: replace-cross Abstract: The exploration-exploitation dilemma in reinforcement learning (RL) is a fundamental challenge to effi

ArXiv cs.AI 🎮 Reinforcement Learning 📄 Paper ⚡ AI Lesson 2w ago

An Introduction to Causal Reinforcement Learning

arXiv:2606.24160v1 Announce Type: new Abstract: Causal inference provides a set of principles and tools that allow one to combine data and knowledge about an en

ArXiv cs.AI 🎮 Reinforcement Learning 📄 Paper ⚡ AI Lesson 2w ago

Learning to Trigger: Reinforcement Learning at the Large Hadron Collider

arXiv:2606.23993v1 Announce Type: cross Abstract: High-throughput scientific facilities such as the Large Hadron Collider depend on real-time event filtering (\

ArXiv cs.AI 🎮 Reinforcement Learning 📄 Paper ⚡ AI Lesson 2w ago

EMAgnet: Parameter-Space EMA Regularization for Policy Gradient Self-Play in Large Games

arXiv:2606.23995v1 Announce Type: cross Abstract: Recent work has established that regularized policy gradient methods such as PPO, when used in self-play, can

ArXiv cs.AI 🎮 Reinforcement Learning 📄 Paper ⚡ AI Lesson 2w ago

IRumAI: Reinforcement Learning for Indian Rummy

arXiv:2606.21975v1 Announce Type: new Abstract: Despite its massive player base and complex hidden-information dynamics, Indian Rummy has received no reinforcem

ArXiv cs.AI 🎮 Reinforcement Learning 📄 Paper ⚡ AI Lesson 2w ago

Select-to-Act: Hierarchical Reinforcement Learning via Adaptive Language Guidance

arXiv:2606.22350v1 Announce Type: cross Abstract: Reinforcement Learning (RL) has been widely applied to sequential decision-making, yet it often suffers from p

ArXiv cs.AI 🎮 Reinforcement Learning 📄 Paper ⚡ AI Lesson 2w ago

Hierarchical Reinforcement Learning for Sparse-Reward Search in Commutative Algebra

arXiv:2606.22922v1 Announce Type: cross Abstract: Applying machine learning techniques to solving long-standing mathematical conjectures can be particularly cha

ArXiv cs.AI 🎮 Reinforcement Learning 📄 Paper ⚡ AI Lesson 3w ago

Stabilizing the Q-Gradient Field for Policy Smoothness in Actor-Critic Methods

arXiv:2601.22970v2 Announce Type: replace-cross Abstract: Policies learned via continuous actor-critic methods often exhibit erratic, high-frequency oscillation

ArXiv cs.AI 🎮 Reinforcement Learning 📄 Paper ⚡ AI Lesson 3w ago

STRIDE: Strategic Trajectory Reasoning via Discriminative Estimation for Verifiable Reinforcement Learning

arXiv:2606.15866v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become an effective post-training paradigm for improvi

ArXiv cs.AI 🎮 Reinforcement Learning 📄 Paper ⚡ AI Lesson 3w ago

Auditing Reward Hackability in Code RL Training Environments

arXiv:2606.16062v1 Announce Type: new Abstract: We measure the rate at which code RL environments accept incorrect solutions as correct. On a 49-task sample of

ArXiv cs.AI 🎮 Reinforcement Learning 📄 Paper ⚡ AI Lesson 3w ago

GAGPO: Generalized Advantage Grouped Policy Optimization

arXiv:2605.13217v1 Announce Type: cross Abstract: Reinforcement learning has become a powerful paradigm for post-training large language model agents, yet credi

ArXiv cs.AI 🎮 Reinforcement Learning 📄 Paper ⚡ AI Lesson 1mo ago

Stubborn: A Streamlined and Unified Reinforcement Learning Framework for Robust Motion Tracking and Fall Recovery for Humanoids

arXiv:2606.12814v1 Announce Type: cross Abstract: Recent reinforcement learning approaches have shown great promise in improving humanoid motion tracking perfor

ArXiv cs.AI 🎮 Reinforcement Learning 📄 Paper ⚡ AI Lesson 1mo ago

PolicyGuard: Towards Test-time and Step-level Adversary Defense for Reinforcement Learning Agent

arXiv:2606.12896v1 Announce Type: cross Abstract: While real-world applications of reinforcement learning (RL) are becoming increasingly popular, the security o

ArXiv cs.AI 🎮 Reinforcement Learning 📄 Paper ⚡ AI Lesson 1mo ago

Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems

arXiv:2505.15201v5 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) algorithms sample multiple n>1 solution attempts for each problem and rewa