Reinforcement - Skytik

Visual Generalization in Reinforcement Learning via Dynamic Object Tokens

March 16, 2026

[Submitted on 12 Aug 2025 (v1), last revised 13 Mar 2026 (this version, v4)] View a PDF of the paper…

A Reinforcement Learning Framework for Long-Horizon Robotic Manipulation with Sparse Reward

March 2, 2026

[Submitted on 15 Aug 2025 (v1), last revised 27 Feb 2026 (this version, v2)] View a PDF of the paper…

Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens

February 19, 2026

[Submitted on 17 Feb 2026 (v1), last revised 18 Feb 2026 (this version, v2)] Authors:Shiqi Liu, Zeyu He, Guojian Zhan,…

[2602.05075] Optimizing Mission Planning for Multi-Debris Rendezvous Using Reinforcement Learning with Refueling and Adaptive Collision Avoidance

February 7, 2026

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals…

Distributed Reinforcement Learning for Scalable High-Performance Policy Optimization

February 1, 2026

on Real-World Problems is Hard Reinforcement learning looks straightforward in controlled settings: well-defined states, dense rewards, stationary dynamics, unlimited simulation.…

[2512.19920] Mitigating LLM Hallucination via Behaviorally Calibrated Reinforcement Learning

January 29, 2026

[Submitted on 22 Dec 2025 (v1), last revised 28 Jan 2026 (this version, v3)] View a PDF of the paper…

Self-Play Reinforcement Learning for Large Language Models with Limited Data

January 27, 2026

[Submitted on 25 May 2025 (v1), last revised 25 Jan 2026 (this version, v2)] View a PDF of the paper…

[2306.07541] A Simple Unified Uncertainty-Guided Framework for Offline-to-Online Reinforcement Learning

January 19, 2026

[Submitted on 13 Jun 2023 (v1), last revised 16 Jan 2026 (this version, v3)] View a PDF of the paper…

Intrinsic Confidence-Driven Group Relative Preference Optimization for Efficient Reinforcement Learning

January 14, 2026

[Submitted on 26 Nov 2025 (v1), last revised 13 Jan 2026 (this version, v5)] View a PDF of the paper…

Enhancing Global Reasoning in Multi-hop Question Answering via Reinforcement Learning

January 13, 2026

[Submitted on 23 Oct 2025 (v1), last revised 12 Jan 2026 (this version, v3)] View a PDF of the paper…

What's Hot

At Least 32 People Dead After a Mine Bridge Collapsed Due to Overcrowding

Here’s how I turned a Raspberry Pi into an in-car media server

Beloved SF cat’s death fuels Waymo criticism

Browsing: Reinforcement

Visual Generalization in Reinforcement Learning via Dynamic Object Tokens

A Reinforcement Learning Framework for Long-Horizon Robotic Manipulation with Sparse Reward

Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens

[2602.05075] Optimizing Mission Planning for Multi-Debris Rendezvous Using Reinforcement Learning with Refueling and Adaptive Collision Avoidance

Distributed Reinforcement Learning for Scalable High-Performance Policy Optimization

[2512.19920] Mitigating LLM Hallucination via Behaviorally Calibrated Reinforcement Learning

Self-Play Reinforcement Learning for Large Language Models with Limited Data

[2306.07541] A Simple Unified Uncertainty-Guided Framework for Offline-to-Online Reinforcement Learning

Intrinsic Confidence-Driven Group Relative Preference Optimization for Efficient Reinforcement Learning

Enhancing Global Reasoning in Multi-hop Question Answering via Reinforcement Learning

At Least 32 People Dead After a Mine Bridge Collapsed Due to Overcrowding

Here’s how I turned a Raspberry Pi into an in-car media server

Beloved SF cat’s death fuels Waymo criticism

Frequency-Aware Planning and Execution Framework for All-in-One Image Restoration

Get threat intelligence to your team fast, in the tools they already use

10 Lead-Generating Mortgage Social Media Posts to Grow Your Sales Pipeline

Hallucinations in LLMs Are Not a Bug in the Data

How to Choose Social Media Networks in 2026

Visual Generalization in Reinforcement Learning via Dynamic Object Tokens

Most Popular

13 Trending Songs on TikTok in Nov 2025 (+ How to Use Them)

How to watch the 2026 GRAMMY Awards online from anywhere

Corporate Reputation Management Strategies | Sprout Social

Our Picks

At Least 32 People Dead After a Mine Bridge Collapsed Due to Overcrowding

Here’s how I turned a Raspberry Pi into an in-car media server

Beloved SF cat’s death fuels Waymo criticism

Subscribe to Updates

What's Hot

Browsing: Reinforcement

Subscribe to Updates