Tagged articles
Policy Optimization
10 articles · Page 1 of 1
This 72-page survey explores how optimal transport provides geometric tools for comparing distributions in reinforcement learning, covering imitation learning, policy optimization, model-based RL, offline RL, robustness, and transfer, while analyzing design choices in cost functions, temporal handling, and computational trade-offs.
Distribution MatchingOffline RLOptimal Transport
0 likes · 35 min read

vivo AI Lab introduces CAPO-SLT, a confidence-aware policy optimization method that stabilizes sign language translation by giving each token a dynamic clipping bound based on old-policy confidence, achieving state-of-the-art results on Chinese and American sign language benchmarks using only pose input.
CSL-DailyEMNLP 2026How2Sign
0 likes · 14 min read

MobileForge introduces an annotation‑free pipeline for adapting mobile GUI agents, combining MobileGym’s exploration‑to‑task generation with HiFPO’s hierarchical feedback‑guided policy optimization, achieving up to 77.6% Pass@3 on AndroidWorld and notable cross‑domain gains without any human‑written tasks or demonstrations.
GUI AgentGUI-OwlHierarchical Feedback
0 likes · 18 min read

GIPO (Gaussian Importance Sampling Policy Optimization) replaces PPO’s hard clipping with a smooth Gaussian‑weighted trust region, achieving log‑space symmetry and bias‑variance balance that mitigates policy lag and utilization collapse, and demonstrates superior stability and sample efficiency on GridWorld, LIBERO, MetaWorld, and 7‑billion‑parameter VLA experiments.
Bias-Variance TradeoffGIPOPolicy Optimization
0 likes · 17 min read

The paper revisits cross-domain offline reinforcement learning, showing that aligning both dynamics and value of source data is essential for effective policy transfer, and introduces the DVDF framework that jointly filters source samples, achieving consistent performance gains across multiple robotic control benchmarks.
Cross-Domain TransferDVDFOffline Reinforcement Learning
0 likes · 13 min read

After DPO, the typical research trajectory moves through GRPO, DAPO, GSPO, and SAPO, each introducing new optimization objectives, sampling strategies, and reward‑shaping techniques that aim to reduce memory usage, improve gradient stability, and enhance the efficiency of large‑model reinforcement learning.
DAPOGRPOGSPO
0 likes · 6 min read

This article explains the fundamental architecture of reinforcement learning, contrasting model‑free and model‑based approaches, detailing environment models, planning, data augmentation, expert iteration, and embedding planning, and then examines how large language models use policy‑based methods such as PPO, DPO, and GRPO for RL‑HF.
Model-BasedModel-freePolicy Optimization
0 likes · 13 min read

The article introduces GVPO, a Group Variance Policy Optimization method that uniquely achieves KL‑constrained reward maximization, supports diverse sampling distributions, and resolves instability and inefficiency issues found in GRPO and traditional policy‑gradient approaches for large language model post‑training.
GVPOKL constraintPolicy Optimization
0 likes · 9 min read

The article reviews reinforcement-learning fundamentals and the progression from policy-gradient to PPO, then introduces Group Relative Policy Optimization (GRPO)—a critic-free method that normalizes rewards across multiple sampled outputs to compute group-relative advantages—and shows how DeepSeek-R1 leverages GRPO with rule-based rewards to achieve strong reasoning performance.
GRPOPPOPolicy Optimization
0 likes · 16 min read

Reinforcement learning, a branch of artificial intelligence, is explained through its core concepts, successful case studies such as AlphaGo and AlphaStar, practical application workflows, current challenges, resources, and future outlook, offering a comprehensive guide for researchers and practitioners.
ApplicationsPolicy OptimizationReinforcement Learning
0 likes · 56 min read
