相关论文: Transfer of Fully Convolutional Policy-Value Netwo…

Combinations of Monte-Carlo tree search and Deep Neural Networks, trained through self-play, have produced state-of-the-art results for automated game-playing in many board games. The training and search algorithms are not game-specific,…

In this work, we ask the following question: Can visual analogies, learned in an unsupervised way, be used in order to transfer knowledge between pairs of games and even play one game using an agent trained for another game? We attempt to…

We present three game-playing agents incorporating Vision Transformers (ViT) into the AlphaZero framework: AlphaViT, AlphaViD (AlphaViT with a transformer decoder), and AlphaVDA (AlphaViD with learnable action embeddings). These agents can…

A general approach to knowledge transfer is introduced in which an agent controlled by a neural network adapts how it reuses existing networks as it learns in a new domain. Networks trained for a new domain can improve their performance by…

Many games often share common ideas or aspects between them, such as their rules, controls, or playing area. However, in the context of General Game Playing (GGP) for board games, this area remains under-explored. We propose to formalise…

We evaluate the use of original game curricula supported by the Atari 2600 console as a heterogeneous transfer benchmark for deep reinforcement learning agents. Game designers created curricula using combinations of several discrete…

This paper explores the use of deep reinforcement learning agents to transfer knowledge from one environment to another. More specifically, the method takes advantage of asynchronous advantage actor critic (A3C) architecture to generalize a…

Being able to reach any desired location in the environment can be a valuable asset for an agent. Learning a policy to navigate between all pairs of states individually is often not feasible. An all-goals updating algorithm uses each…

In many board games and other abstract games, patterns have been used as features that can guide automated game-playing agents. Such patterns or features often represent particular configurations of pieces, empty positions, etc., which may…

This work investigates the adaptation of the AlphaZero reinforcement learning algorithm to Tablut, an asymmetric historical board game featuring unequal piece counts and distinct player objectives (king capture versus king escape). While…

We develop a method of adapting the AlphaZero model to General Game Playing (GGP) that focuses on faster model generation and requires less knowledge to be extracted from the game rules. The dataset generation uses MCTS playing instead of…

Deep reinforcement learning has proven to be successful for learning tasks in simulated environments, but applying same techniques for robots in real-world domain is more challenging, as they require hours of training. To address this,…

We explore the capability of evolution strategies to train an agent with a policy based on a transformer architecture in a reinforcement learning setting. We performed experiments using OpenAI's highly parallelizable evolution strategy to…

We develop a method for the transfer of perfect strategies between various classes of two-player, one round cooperative non-local games with quantum inputs and outputs using the simulation paradigm in quantum information theory. We show…

This paper explores successor features for knowledge transfer in zero-sum, complete-information, and turn-based games. Prior research in single-agent systems has shown that successor features can provide a ``jump start" for agents when…

The Digital Ludeme Project (DLP) aims to reconstruct and analyse over 1000 traditional strategy games using modern techniques. One of the key aspects of this project is the development of Ludii, a general game system that will be able to…

The AlphaZero algorithm for the learning of strategy games via self-play, which has produced superhuman ability in the games of Go, chess, and shogi, uses a quantitative reward function for game outcomes, requiring the users of the…

In this work we explore the use of latent representations obtained from multiple input sensory modalities (such as images or sounds) in allowing an agent to learn and exploit policies over different subsets of input modalities. We propose a…

Automatically generating novel and interesting games is a complex task. Challenges include representing game rules in a computationally workable form, searching through the large space of potential games under most such representations, and…

Neural Networks as fast physics simulators have a large potential for many engineering design tasks. Prerequisites for a wide-spread application are an easy-to-use workflow for generating training datasets in a reasonable time, and the…