arXiv Machine Learning
Hierarchical Deep Counterfactual Regret Minimization
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Oct 2
Finetuning with Sampling: SFT Learns Better Than You Think
The paper introduces a Markov chain Monte Carlo (MCMC) sampling algorithm that transforms off‑policy traces into more on‑policy data for supervised finetuning (SFT). By tailoring the data distribution rather than changing the learning objective, the method allows SFT to match or surpass traditional post‑training techniques such as reinforcement learning across tasks like scientific skill acquisition, mathematical reasoning, and open‑ended expertise. The resulting models generalize better, forget less, and exhibit strong distributional performance, demonstrating that sampling can serve as a model‑native operator for broader post‑training applications.
arXiv Machine Learning
Oct 2
Learning High-Risk High-Precision Motion Control
arXiv:2609.34851v2 Announce Type: replace Abstract: Deep reinforcement learning (DRL) algorithms for movement control are typically evaluated and benchmarked on sequential decision tasks where imprec...
arXiv Machine Learning
Sep 18
EmbodiedMind: Adaptive Data Curation and Prefix-Tree Reinforcement Learning for Efficient Embodied Intelligence
EmbodiedMind introduces a three-stage training paradigm for embodied foundation models that tackles inefficient sample use, task imbalance, and credit assignment in long-horizon planning. The stages—Rejection Sampling-based Fine‑Tuning, Iterative Rejection GRPO, and Trie‑GRPO—filter low‑informative data, balance task difficulty, and use action prefix trees for step‑level advantage estimation. This approach yields a state‑of‑the‑art average performance of 70.02% across 18 benchmarks, notably improving long‑horizon task planning accuracy.
arXiv AI
Aug 21
Learning Hierarchical Skill Policies with Offline Quality-Diversity Reinforcement Learning
arXiv:2608. 19684v1 Announce Type: new Abstract: Recent studies investigate how to leverage pre-collected datasets to improve the policy performance and sample efficiency of RL.
arXiv AI
Jun 15
Unsupervised Learning of Efficient Exploration: Pre-training Adaptive Policies via Self-Imposed Goals
arXiv:2601. 19810v2 Announce Type: replace-cross Abstract: Unsupervised pre-training can equip reinforcement learning agents with prior knowledge and accelerate learning in downstream tasks.
arXiv Machine Learning
Oct 7
Direct Regret Optimization in Bayesian Optimization
arXiv:2507.06529v2 Announce Type: replace Abstract: Bayesian optimization (BO) is a powerful paradigm for optimizing expensive black-box functions. Traditional BO methods typically rely on separate h...