paper-with-me

Papers

OptionZero: Planning with Learned Options

2025-02-23 · Po-Wei Huang, Pei-Chiun Peng, Hung Guei, Ti-Rong Wu

Planning with options -- a sequence of primitive actions -- has been shown effective in reinforcement learning within complex environments. Previous studies have focused on planning with predefined options or learned options through expert demonstration data. Inspired by MuZero, which learns superhuman heuristics without any human knowledge, we propose a novel approach, named OptionZero. OptionZero incorporates an option network into MuZero, providing autonomous discovery of options through self-play games. Furthermore, we modify the dynamics network to provide environment transitions when using options, allowing searching deeper under the same simulation constraints. Empirical experiments conducted in 26 Atari games demonstrate that OptionZero outperforms MuZero, achieving a 131.58% improvement in mean human-normalized score. Our behavior analysis shows that OptionZero not only learns options but also acquires strategic skills tailored to different game characteristics. Our findings show promising directions for discovering and using options in planning. Our code is available at https://rlg.iis.sinica.edu.tw/papers/optionzero.

📄 PDF Abstract BibTeX arXiv:2502.16634

Code (1)

rlglab/optionzero 공식 구현

Tasks

Atari Games

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Batch Normalization 설명 없음
Average Pooling 설명 없음
Prioritized Experience Replay Prioritized Experience Replay is a type of experience replay in reinforcement learning where we more frequently replay…
Residual Connection 설명 없음
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…
Monte-Carlo Tree Search Monte-Carlo Tree Search is a planning algorithm that accumulates value estimates obtained from Monte Carlo simulations in order to successively direct simulations towards more…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

GrASP: Gradient-Based Affordance Selection for Planning

2022-02-08 · Vivek Veeriah, Zeyu Zheng, Richard Lewis, Satinder Singh

Planning with a learned model is arguably a key component of intelligence. There are several challenges in realizing such a component in large-scale reinforcement learning (RL) problems. One such challenge is dealing eff…

Reinforcement Learning (RL)

Reward-Respecting Subtasks for Model-Based Reinforcement Learning

2022-02-07 · Richard S. Sutton, Marlos C. Machado, G. Zacharias Holland, David Szepesvari 외

To achieve the ambitious goals of artificial intelligence, reinforcement learning must include planning with a model of the world that is abstract in state and time. Deep learning has made progress with state abstraction…

Model-based Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Iterative Option Discovery for Planning, by Planning

2023-10-02 · Kenny Young, Richard S. Sutton

Discovering useful temporal abstractions, in the form of options, is widely thought to be key to applying reinforcement learning and planning to increasingly complex domains. Building on the empirical success of the Expe…

Creativity of AI: Hierarchical Planning Model Learning for Facilitating Deep Reinforcement Learning

2021-12-18 · Hankz Hankui Zhuo, Shuting Deng, Mu Jin, Zhihao Ma 외

Despite of achieving great success in real-world applications, Deep Reinforcement Learning (DRL) is still suffering from three critical issues, i.e., data efficiency, lack of the interpretability and transferability. Rec…

Deep Reinforcement LearningMontezuma's Revengereinforcement-learningReinforcement Learning+1

Learning Options from Demonstration using Skill Segmentation

2020-01-19 · Matthew Cockcroft, Shahil Mawjee, Steven James, Pravesh Ranchod

We present a method for learning options from segmented demonstration trajectories. The trajectories are first segmented into skills using nonparametric Bayesian clustering and a reward function for each segment is then …

Clusteringreinforcement-learningReinforcement LearningReinforcement Learning (RL)