Scalable Online Planning via Reinforcement Learning Fine-Tuning

2021-09-30 · NeurIPS 2021 12 · Arnaud Fickinger, Hengyuan Hu, Brandon Amos, Stuart Russell, Noam Brown

Lookahead search has been a critical component of recent AI successes, such as in the games of chess, go, and poker. However, the search methods used in these games, and in many other settings, are tabular. Tabular search methods do not scale well with the size of the search space, and this problem is exacerbated by stochasticity and partial observability. In this work we replace tabular search with online model-based fine-tuning of a policy neural network via reinforcement learning, and show that this approach outperforms state-of-the-art search algorithms in benchmark settings. In particular, we use our search algorithm to achieve a new state-of-the-art result in self-play Hanabi, and show the generality of our algorithm by also showing that it outperforms tabular search in the Atari game Ms. Pacman.

📄 PDF Abstract BibTeX arXiv:2109.15316

Code (1)

facebookresearch/off-belief-learning pytorch

Tasks

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

ReinforceGen: Hybrid Skill Policies with Automated Data Generation and Reinforcement Learning

2025-12-18 · Zihan Zhou, Animesh Garg, Ajay Mandlekar, Caelan Garrett arxiv

Long-horizon manipulation has been a long-standing challenge in the robotics community. We propose ReinforceGen, a system that combines task decomposition, data generation, imitation learning, and motion planning to form…

Reinforcement Learning Motion Planning

AdaWM: Adaptive World Model based Planning for Autonomous Driving

2025-01-22 · Hang Wang, Xin Ye, Feng Tao, Chenbin Pan 외

World model based reinforcement learning (RL) has emerged as a promising approach for autonomous driving, which learns a latent dynamics model and uses it to train a planning policy. To speed up the learning process, the…

Autonomous Driving Model-based Reinforcement Learning Reinforcement Learning (RL)

Scalable Planning and Learning for Multiagent POMDPs: Extended Version

2014-04-04 · Christopher Amato, Frans A. Oliehoek

Online, sample-based planning algorithms for POMDPs have shown great promise in scaling to problems with large state spaces, but they become intractable for large action and observation spaces. This is particularly probl…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Simulation Distillation: Pretraining World Models in Simulation for Rapid Real-World Adaptation

2026-03-16 · Jacob Levy, Tyler Westenbroek, Kevin Huang, Fernando Palafox 외 arxiv

Robot learning requires adaptation methods that improve reliably from limited, mixed-quality interaction data. This is especially challenging in long-horizon, contact-rich tasks, where end-to-end policy finetuning remain…

Action-Factored Multi-Agent Reinforcement Learning for Scalable Quantum Device Tuning

2026-07-10 · Edwin De Nicolo, Rahul Marchand, Cornelius Carlsson, Pranav Vaidhyanathan 외 arxiv

Cooperative multi-agent reinforcement learning is well suited to problems with large parameter spaces and exploitable local structure, such as the tuning of electrostatically-defined quantum-dot arrays. However, if param…

Multi-agent Reinforcement Learning Zero-shot Generalization