← Back to all news

Reinforcement learning

Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.

6,856 stories · RSS feed

arXiv Computer Vision
Sep 23

Sometimes You Gotta Run Before You Can Walk: Run-then-Walk Scheduling Strategy for VLM Autonomous Driving

arXiv:2609.25831v1 Announce Type: cross Abstract: Recent VLM-based autonomous driving planners adopt GRPO-style reinforcement learning to optimize driving performance. However, existing GRPO recipes...

By Yuqi Ye, Shangkun Sun, Junhong Lin, Jiayi Zhao, Changhao Peng, Wei Zheng, Guoqing Liu, Tiesong Zhao, Wei Gao
agentsreinforcement-learningroboticsmultimodalbenchmarkssafety
More like this →
arXiv AI
Sep 23

Synthesizing Reactive Character Behaviors for Continuous Games via Programmatic Policy Search

The paper introduces a method for creating reactive character behaviors in continuous games as compact, human‑readable programs. It searches over a domain‑specific language that uses reactive geometric decisions and higher‑order constructs to discretize continuous behavior space, while eliminating redundant program forms through synthesis antipatterns. The approach, called agentic sketching, combines bottom‑up symbolic enumeration with top‑down guidance from a coding agent, and outperforms either technique alone on a benchmark of 14 continuous games.

By Maxim Gumin, Hsueh-Ti Derek Liu, Victor Zordan, Daniel Ritchie
agentsreinforcement-learningbenchmarks
More like this →
arXiv Machine Learning
Sep 23

Optimal Sequential Annotations for Off-Policy Evaluation

The paper proposes a method for allocating a limited budget of expert annotations to optimize the accuracy of off-policy evaluation in settings where rewards are missing or noisy. By deriving variance‑optimal annotation probabilities for sequential, forward‑monotone protocols, the authors provide a batch‑adaptive implementation that can be applied to real data. Experiments on casenotes from a homelessness services nonprofit and on human‑preference votes from LMArena demonstrate substantial reductions in RMSE—up to 65% for housing placement and 68% for progress toward a housing application—when using only 40% or more of the full annotation budget.

By Woojin Chae, Ezinne Nwankwo, Haitong Qin, Angela Zhou
llmsreinforcement-learningsafety
More like this →
arXiv Machine Learning
Sep 23

Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning

Agent0 is a fully autonomous framework that enables large language model agents to evolve without external data by using a multi‑step co‑evolution process. It pits a curriculum agent against an executor agent, both derived from the same base LLM, where the curriculum agent creates increasingly challenging tasks and the executor learns to solve them. By integrating external tools into the executor’s workflow, the system creates a self‑reinforcing cycle that continuously generates high‑quality curricula, leading to significant gains in reasoning performance—an 18% improvement on mathematical reasoning and 24% on general reasoning for the Qwen3‑8B‑Base model.

By Peng Xia, Kaide Zeng, Jiaqi Liu, Can Qin, Fang Wu, Yiyang Zhou, Caiming Xiong, Huaxiu Yao
llmsagentsreinforcement-learningbenchmarks
More like this →
arXiv AI
Sep 23

Spiking Neural Network Actor-Critic Proximal Policy Optimization Control for Autonomous UAV Navigation Through Constrained Openings in Civil Infrastructure and Buildings

The paper presents a spiking neural network-based Proximal Policy Optimization (SNN‑PPO) algorithm for autonomous UAV navigation through constrained openings in civil infrastructure. By integrating spike‑based actor‑critic reinforcement learning with a stochastic Gaussian policy, the method achieved 63.77 % overall success across 3000+ episodes, improving to over 90 % in later stages and averaging 2.10 windows per episode.

By Francis Noah Walugembe, Maciej Wielgosz, Toma\v{z} Gori\v{c}an, Matej Mertik
agentsreinforcement-learningrobotics
More like this →
arXiv Machine Learning
Sep 23

A Decentralized Partially Observable Team Decision Methodology with Delayed Information Sharing

The paper introduces a decentralized decision-making framework for teams operating under partial observability and unknown system dynamics. By leveraging low-rank latent dynamics and delayed shared information, each team member learns an approximate Markov decision process using only local private data and delayed common updates. The resulting algorithm achieves near‑optimal team performance without requiring a centralized coordinator or training, and the authors provide finite‑sample guarantees and a sample‑complexity bound.

By Xiaoxing Ren, Thomas Parisini, Andreas A. Malikopoulos
reinforcement-learning
More like this →
arXiv Machine Learning
Sep 23

Tight Sample Complexity Bounds for Entropic Best Policy Identification

The paper investigates best‑policy identification in finite‑horizon, risk‑sensitive reinforcement learning using the entropic risk measure. It identifies a gap between known lower bounds ≥ η(e^{|eta|H}) and upper bounds ≤ O(e^{2|eta|H}) for sample complexity, attributing the excess factor to loose concentration bounds for exponential utilities. By employing a forward‑model algorithm with KL‑based exploration bonuses and a novel stopping rule, the authors achieve a sample complexity that matches the lower bound, closing the previously open exponential gap.

By Amer Essakine, Claire Vernade
reinforcement-learningbenchmarks
More like this →