paper-with-me

Papers

Accelerating Empowerment Computation with UCT Tree Search

2018-03-27 · Christoph Salge, Christian Guckelsberger, Rodrigo Canaan, Tobias Mahlmann

Models of intrinsic motivation present an important means to produce sensible behaviour in the absence of extrinsic rewards. Applications in video games are varied, and range from intrinsically motivated general game-playing agents to non-player characters such as companions and enemies. The information-theoretic quantity of Empowerment is a particularly promising candidate motivation to produce believable, generic and robust behaviour. However, while it can be used in the absence of external reward functions that would need to be crafted and learned, empowerment is computationally expensive. In this paper, we propose a modified UCT tree search method to mitigate empowerment's computational complexity in discrete and deterministic scenarios. We demonstrate how to modify a Monte-Carlo Search Tree with UCT to realise empowerment maximisation, and discuss three additional modifications that facilitate better sampling. We evaluate the approach both quantitatively, by analysing how close our approach gets to the baseline of exhaustive empowerment computation with varying amounts of computational resources, and qualitatively, by analysing the resulting behaviour in a Minecraft-like scenario.

📄 PDF Abstract BibTeX arXiv:1803.09866

Code (0)

등록된 구현이 없습니다.

Tasks

Minecraft

Similar Papers 제목 키워드 기반

Empowerment Gain and Causal Model Construction: Children and adults are sensitive to controllability and variability in their causal interventions

2025-12-09 · Eunice Yiu, Kelsey Allen, Shiry Ginosar, Alison Gopnik arxiv

Learning about the causal structure of the world is a fundamental problem for human cognition. Causal models and especially causal learning have proved to be difficult for large pretrained models using standard technique…

Reinforcement Learning

Improved Monte Carlo tree search formulation with multiple root nodes for discrete sizing optimization of truss structures

2023-09-12 · Fu-Yao Ko, Katsuyuki Suzuki, Kazuo Yonekura

This paper proposes a novel reinforcement learning (RL) algorithm using improved Monte Carlo tree search (IMCTS) formulation for discrete optimum design of truss structures. IMCTS with multiple root nodes includes update…

Reinforcement Learning (RL)

In Search of a Lost Metric: Human Empowerment as a Pillar of Socially Conscious Navigation

2025-01-02 · Vasanth Reddy Baddam, Behdad Chalaki, Vaishnav Tadiparthi, Hossein Nourkhiz Mahjoub 외

In social robot navigation, traditional metrics like proxemics and behavior naturalness emphasize human comfort and adherence to social norms but often fail to capture an agent's autonomy and adaptability in dynamic envi…

Robot NavigationSocial Navigation

Information-Theoretic Policy Pre-Training with Empowerment

2025-10-07 · Moritz Schneider, Robert Krug, Narunas Vaskevicius, Luigi Palmieri 외 arxiv

Empowerment, an information-theoretic measure of an agent's potential influence on its environment, has emerged as a powerful intrinsic motivation and exploration framework for reinforcement learning (RL). Besides for un…

Reinforcement Learning

Accelerating Monte Carlo Tree Search with Probability Tree State Abstraction

2023-10-10 · NeurIPS 2023 11

Monte Carlo Tree Search (MCTS) algorithms such as AlphaGo and MuZero have achieved superhuman performance in many challenging tasks. However, the computational complexity of MCTS-based algorithms is influenced by the siz…