Experience-Driven PCG via Reinforcement Learning: A Super Mario Bros Study

2021-06-30 · Tianye Shu, Jialin Liu, Georgios N. Yannakakis

We introduce a procedural content generation (PCG) framework at the intersections of experience-driven PCG and PCG via reinforcement learning, named ED(PCG)RL, EDRL in short. EDRL is able to teach RL designers to generate endless playable levels in an online manner while respecting particular experiences for the player as designed in the form of reward functions. The framework is tested initially in the Super Mario Bros game. In particular, the RL designers of Super Mario Bros generate and concatenate level segments while considering the diversity among the segments. The correctness of the generation is ensured by a neural net-assisted evolutionary level repairer and the playability of the whole level is determined through AI-based testing. Our agents in this EDRL implementation learn to maximise a quantification of Koster's principle of fun by moderating the degree of diversity across level segments. Moreover, we test their ability to design fun levels that are diverse over time and playable. Our proposed framework is capable of generating endless, playable Super Mario Bros levels with varying degrees of fun, deviation from earlier segments, and playability. EDRL can be generalised to any game that is built as a segment-based sequential process and features a built-in compressed representation of its game content.

📄 PDF Abstract BibTeX arXiv:2106.15877

Code (1)

SliverySky/mariopuzzle 공식 구현 pytorch

Tasks

Diversityreinforcement-learning Reinforcement Learning (RL)

Super Reinforcement Bros: Playing Super Mario Bros with Reinforcement Learning

2020-12-14 · CUHK Course IERG5350 2020 12 · Nan Zhang, Zixing Song

We plan to apply and adjust some well-known reinforcement learning (RL) algorithms to train an automatic agent to play the 1985 Nintendo game Super Mario Bros under a speedrun rule. The agent may learn several control po…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Improving Deep Localized Level Analysis: How Game Logs Can Help

2022-12-07 · Natalie Bombardieri, Matthew Guzdial

Player modelling is the field of study associated with understanding players. One pursuit in this field is affect prediction: the ability to predict how a game will make a player feel. We present novel improvements to af…

RAMario: Experimental Approach to Reptile Algorithm -- Reinforcement Learning for Mario

2023-05-16 · Sanyam Jain

This research paper presents an experimental approach to using the Reptile algorithm for reinforcement learning to train a neural network to play Super Mario Bros. We implement the Reptile algorithm using the Super Mario…

Few-Shot Learning Meta-Learning reinforcement-learning Reinforcement Learning

Generating Game Levels of Diverse Behaviour Engagement

2022-07-05 · Keyuan Zhang, Jiayu Bai, Jialin Liu

Recent years, there has been growing interests in experience-driven procedural level generation. Various metrics have been formulated to model player experience and help generate personalised levels. In this work, we que…

State Space Closure: Revisiting Endless Online Level Generation via Reinforcement Learning

2022-12-06 · Ziqi Wang, Tianye Shu, Jialin Liu

In this paper, we revisit endless online level generation with the recently proposed experience-driven procedural content generation via reinforcement learning (EDRL) framework. Inspired by an observation that EDRL tends…

Diversity reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)