Learning and Planning in Complex Action Spaces

2021/04/13 by Thomas Hubert, Hubert, Thomas, Julian Schrittwieser +9 · 9 citations
Computer Science · #Artificial Intelligence in Games #Evolutionary Algorithms and Applications #FOS: Computer and information sciences #Machine Learning (cs.LG) #Reinforcement Learning in Robotics

paper · pdf · doi:10.48550/arxiv.2104.06303

openalex publication_date 2021/04/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Many important real-world problems have action spaces that are high-dimensional, continuous or both, making full enumeration of all possible actions infeasible. Instead, only small subsets of actions can be sampled for the purpose of policy evaluation and improvement. In this paper, we propose a general framework to reason in a principled way about policy evaluation and improvement over such sampled action subsets. This sample-based policy iteration framework can in principle be applied to any reinforcement learning algorithm based upon policy iteration. Concretely, we propose Sampled MuZero, an extension of the MuZero algorithm that is able to learn in domains with arbitrarily complex action spaces by planning over sampled actions. We demonstrate this approach on the classical board game of Go and on two continuous control benchmark domains: DeepMind Control Suite and Real-World RL Suite.

Citations

• DeepStack: Expert-level artificial intelligence in heads-up no-limit poker
• DeepMind Control Suite
• Dream to Control: Learning Behaviors by Latent Imagination
• An operator view of policy gradient methods

Cited by

• Parallelizing Tree Search with Twice Sequential Monte Carlo
• Online and Offline Reinforcement Learning by Planning with a Learned Model
• Who Gets the Reward, Who Gets the Blame? Evaluation-Aligned Training Signals for Multi-LLM Agents
• MALinZero: Efficient Low-Dimensional Search for Mastering Complex Multi-Agent Planning
• Controllable Graph Generation with Diffusion Models via Inference-Time Tree Search Guidance
• Learning Large Neighborhood Search Policy for Integer Programming
• One Model for All Tasks: Leveraging Efficient World Models in Multi-Task Planning
• floq: Training Critics via Flow-Matching for Scaling Compute in Value-Based RL
• Improving Pre-Trained Vision-Language-Action Policies with Model-Based Search

Related

• Growing Action Spaces
• Continuous Control for Searching and Planning with a Learned Model
• Learning in complex action spaces without policy gradients
• Computationally Efficient Reinforcement Learning: Targeted Exploration leveraging Simple Rules
• Theoretically Guaranteed Policy Improvement Distilled from Model-Based Planning