paper-with-me

Papers

What model does MuZero learn?

2023-06-01 · Jinke He, Thomas M. Moerland, Joery A. de Vries, Frans A. Oliehoek

Model-based reinforcement learning (MBRL) has drawn considerable interest in recent years, given its promise to improve sample efficiency. Moreover, when using deep-learned models, it is possible to learn compact and generalizable models from data. In this work, we study MuZero, a state-of-the-art deep model-based reinforcement learning algorithm that distinguishes itself from existing algorithms by learning a value-equivalent model. Despite MuZero's success and impact in the field of MBRL, existing literature has not thoroughly addressed why MuZero performs so well in practice. Specifically, there is a lack of in-depth investigation into the value-equivalent model learned by MuZero and its effectiveness in model-based credit assignment and policy improvement, which is vital for achieving sample efficiency in MBRL. To fill this gap, we explore two fundamental questions through our empirical analysis: 1) to what extent does MuZero achieve its learning objective of a value-equivalent model, and 2) how useful are these models for policy improvement? Our findings reveal that MuZero's model struggles to generalize when evaluating unseen policies, which limits its capacity for additional policy improvement. However, MuZero's incorporation of the policy prior in MCTS alleviates this problem, which biases the search towards actions where the model is more accurate.

📄 PDF Abstract BibTeX arXiv:2306.00840

Code (0)

등록된 구현이 없습니다.

Tasks

modelModel-based Reinforcement Learningreinforcement-learningReinforcement Learning

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…
Residual Connection 설명 없음
Prioritized Experience Replay Prioritized Experience Replay is a type of experience replay in reinforcement learning where we more frequently replay…
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…
Average Pooling 설명 없음
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…
Batch Normalization 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…

Similar Papers 제목 키워드 기반

Visualizing MuZero Models

2021-02-25 · ICML Workshop URL 2021 7 · Joery A. de Vries, Ken S. Voskuil, Thomas M. Moerland, Aske Plaat

MuZero, a model-based reinforcement learning algorithm that uses a value equivalent dynamics model, achieved state-of-the-art performance in Chess, Shogi and the game of Go. In contrast to standard forward dynamics model…

Game of GoModel-based Reinforcement Learning

On the role of planning in model-based deep reinforcement learning

2020-11-08 · ICLR 2021 1 · Jessica B. Hamrick, Abram L. Friesen, Feryal Behbahani, Arthur Guez 외

Model-based planning is often thought to be necessary for deep, careful reasoning and generalization in artificial agents. While recent successes of model-based reinforcement learning (MBRL) with deep function approximat…

Deep Reinforcement LearningModel-based Reinforcement Learningreinforcement-learningReinforcement Learning+1

Interpreting the Learned Model in MuZero Planning

2024-11-07 · Hung Guei, Yan-Ru Ju, Wei-Yu Chen, Ti-Rong Wu

MuZero has achieved superhuman performance in various games by using a dynamics network to predict environment dynamics for planning, without relying on simulators. However, the latent states learned by the dynamics netw…

Atari GamesBoard Gamesmodel

Online and Offline Reinforcement Learning by Planning with a Learned Model

2021-04-13 · NeurIPS 2021 12 · Julian Schrittwieser, Thomas Hubert, Amol Mandhane, Mohammadamin Barekatain 외

Learning efficiently from small amounts of data has long been the focus of model-based reinforcement learning, both for the online case when interacting with the environment and the offline case when learning from a fixe…

Atari GamesContinuous ControlModel-based Reinforcement LearningOffline RL+3

Combining Off and On-Policy Training in Model-Based Reinforcement Learning

2021-02-24 · Alexandre Borges, Arlindo Oliveira

The combination of deep learning and Monte Carlo Tree Search (MCTS) has shown to be effective in various domains, such as board and video games. AlphaGo represented a significant step forward in our ability to learn comp…

Atari GamesBoard GamesModel-based Reinforcement Learningreinforcement-learning+1