arXiv Machine Learning June 4, 2026 By Marc Walden, Jason Liu, Shaashwath Sivakumar, Ryan Liu, Hamza Khan

Enhancing the MADDPG Algorithm for Multi-Agent Learning via Action Inference and Importance Sampling

Read the original on arXiv Machine Learning →

arXiv:2606. 05021v1 Announce Type: new Abstract: We investigate multi-agent deep reinforcement learning and propose two enhancements to the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 5

Training One Model to Master Cross-Level Agentic Actions via Reinforcement Learning

arXiv:2512. 09706v2 Announce Type: replace Abstract: The paradigm of agentic AI is shifting from engineered complex workflows to post-training native models.

By Kaichen He, Zihao Wang, Muyao Li, Anji Liu, Yitao Liang

agents reinforcement-learning robotics fine-tuning benchmarks

arXiv AI

Aug 3

Gated Q-learning: Add Off-Policy Bias to Taste

arXiv:2607. 28916v1 Announce Type: cross Abstract: Multistep credit assignment is critical for sample-efficient reinforcement learning, yet managing off-policy bias in Q-learning remains a fundamental challenge.

By Brett Daley

agents reinforcement-learning safety

arXiv AI

4d ago

Learn from the Gap: Differential-Aware Advantage Pruning with Adaptive Rollout Sampling for GRPO

The paper introduces FastRL, a reinforcement learning framework designed to enhance the efficiency of Group Relative Policy Optimization (GRPO) and its variants. FastRL employs an advantage-aware pruning strategy that retains high-advantage trajectories while preserving gradient diversity, and an adaptive rollout sampling mechanism that adjusts sampling scale during training based on historical pruning data. Experiments show that FastRL can be integrated into GRPO, DAPO, and GSPO, yielding a 2.07× speedup on Geometry3K and GeoQA8K-R1V and a 1.64% accuracy improvement on visual reasoning benchmarks.

By Jiahua Yang, Zhiwei Yang, Xianpeng Zhang, Dongyu Chen, Xing Chen, Tianhuang Su, Haonan Lu, Quanlong Guan, Kai Tang, Chuangchuang Wang

reinforcement-learning efficiency benchmarks

arXiv AI

Jul 22

Comparative Study of Multi-Agent Actor-Critic Algorithms in Parameterized Action Reinforcement Learning

arXiv:2607. 19117v1 Announce Type: new Abstract: Parameterized action reinforcement learning has shown strong performance in environments requiring both discrete action selection and continuous parameterization.

By Ubayd Ali Bapoo, Clement N Nyirenda

agents reinforcement-learning benchmarks

arXiv Machine Learning

Jun 19

Direct Advantage Estimation for Scalable and Sample-efficient Deep Reinforcement Learning

arXiv:2606. 20411v1 Announce Type: new Abstract: Direct Advantage Estimation (DAE) has been shown to improve the sample efficiency of deep reinforcement learning algorithms.

By Hsiao-Ru Pan, Bernhard Sch\"olkopf

reinforcement-learning

arXiv AI

Jun 16

Safe Exploration via Policy Priors

arXiv:2601. 19612v3 Announce Type: replace-cross Abstract: Safe exploration is a key requirement for reinforcement learning (RL) agents to learn and adapt online, beyond controlled (e.

By Manuel Wendl, Yarden As, Manish Prajapat, Anton Pollak, Stelian Coros, Andreas Krause

agents reinforcement-learning benchmarks safety

One email a morning, machine-written

Related stories

Training One Model to Master Cross-Level Agentic Actions via Reinforcement Learning

Gated Q-learning: Add Off-Policy Bias to Taste

Learn from the Gap: Differential-Aware Advantage Pruning with Adaptive Rollout Sampling for GRPO

Comparative Study of Multi-Agent Actor-Critic Algorithms in Parameterized Action Reinforcement Learning

Direct Advantage Estimation for Scalable and Sample-efficient Deep Reinforcement Learning

Safe Exploration via Policy Priors