Transfer of Fully Convolutional Policy-Value Networks Between Games and Game Variants

2021-02-24 · Dennis J. N. J. Soemers, Vegard Mella, Eric Piette, Matthew Stephenson, Cameron Browne, Olivier Teytaud

In this paper, we use fully convolutional architectures in AlphaZero-like self-play training setups to facilitate transfer between variants of board games as well as distinct games. We explore how to transfer trained parameters of these architectures based on shared semantics of channels in the state and action representations of the Ludii general game system. We use Ludii's large library of games and game variants for extensive transfer learning evaluations, in zero-shot transfer experiments as well as experiments with additional fine-tuning time.

📄 PDF Abstract BibTeX arXiv:2102.12375

Code (0)

등록된 구현이 없습니다.

Tasks

Board GamesTransfer Learning

Successor Features for Transfer in Reinforcement Learning

2016-06-16 · NeurIPS 2017 12 · André Barreto, Will Dabney, Rémi Munos, Jonathan J. Hunt 외

Transfer in reinforcement learning refers to the notion that generalization should occur not only within a task but also across tasks. We propose a transfer framework for the scenario where the reward function changes be…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

CURO: Curriculum Learning for Relative Overgeneralization

2022-12-06 · Lin Shi, Qiyuan Liu, Bei Peng

Relative overgeneralization (RO) is a pathology that can arise in cooperative multi-agent tasks when the optimal joint action's utility falls below that of a sub-optimal joint action. RO can cause the agents to get stuck…

Efficient Exploration Multi-agent Reinforcement Learning Starcraft Starcraft II+1

RL-Driven Sustainable Land-Use Allocation for the Lake Malawi Basin

2026-04-04 · Ying Yao arxiv

Unsustainable land-use practices in ecologically sensitive regions threaten biodiversity, water resources, and the livelihoods of millions. This paper presents a deep reinforcement learning (RL) framework for optimizing …

Reinforcement Learning

Multi-agent Policy Reciprocity with Theoretical Guarantee

2023-04-12 · Haozhi Wang, Yinchuan Li, Qing Wang, Yunfeng Shao 외

Modern multi-agent reinforcement learning (RL) algorithms hold great potential for solving a variety of real-world problems. However, they do not fully exploit cross-agent knowledge to reduce sample complexity and improv…

continuous-control Continuous Control Multi-agent Reinforcement Learning Reinforcement Learning (RL)

Soft Value Iteration Networks for Planetary Rover Path Planning

2018-01-01 · ICLR 2018 1 · Max Pflueger, Ali Agha, Gaurav S. Sukhatme

Value iteration networks are an approximation of the value iteration (VI) algorithm implemented with convolutional neural networks to make VI fully differentiable. In this work, we study these networks in the context of …

Motion Planning