Configurable Agent With Reward As Input: A Play-Style Continuum Generation

  title={Configurable Agent With Reward As Input: A Play-Style Continuum Generation},
  author={Pierre Le Pelletier de Woillemont and R{\'e}mi Labory and Vincent Corruble},
  journal={2021 IEEE Conference on Games (CoG)},
Modern video games are becoming richer and more complex in terms of game mechanics. This complexity allows for the emergence of a wide variety of ways to play the game across the players. From the point of view of the game designer, this means that one needs to anticipate a lot of different ways the game could be played. Machine Learning (ML) could help address this issue. More precisely, Reinforcement Learning is a promising answer to the need of automating video game testing. In this paper we… 

Figures and Tables from this paper

Automated Play-Testing through RL Based Human-Like Play-Styles Generation

This work presents CARMI : a Configurable Agent with Relative Metrics as Input, an agent able to emulate the players play-styles, even on previously unseen levels, thus compatible with the constraints of modern video game production.

Towards Informed Design and Validation Assistance in Computer Games Using Imitation Learning

The survey results show that the proposed method is indeed a valid approach to game validation and that data-driven programming would be a useful aid to reducing effort and increasing quality of modern playtesting.

CCP: Configurable Crowd Profiles

This paper presents a RL-based framework for learning multiple agent behaviors concurrently and demonstrates that the proposed model generalizes to situations not seen in the training data such as a) crowds with higher density, b) behavior weights that are outside the training intervals and c) to scenes with more intricate environment layouts.

CCPT: Automatic Gameplay Testing and Validation with Curiosity-Conditioned Proximal Trajectories

This paper proposes a novel deep reinforcement learning algorithm to perform automatic analysis and detection of gameplay issues in complex 3D navigation environments and shows how CCPT can explore complex environments, discover gameplay issues and design oversights in the process, and recognize and highlight them directly to game designers.

Direct Behavior Specification via Constrained Reinforcement Learning

This work argues that constrained RL, which has almost exclusively been used for safe RL, also has the potential to significantly reduce the amount of work spent for reward specification in applied RL projects, and investigates how CMDPs can be adapted to solve goal-based tasks while adhering to several constraints simultaneously.



Sample Efficient Actor-Critic with Experience Replay

This paper presents an actor-critic deep reinforcement learning agent with experience replay that is stable, sample efficient, and performs remarkably well on challenging environments, including the

Defining personas in games using metrics

The concept of play-persona is applied to game metrics, in the specific case of character-based computer games, where the player controls a single protagonist, around whom the gameplay and story evolves.

Automated Playtesting With Procedural Personas Through MCTS With Evolved Heuristics

This paper uses artificially intelligent personas to construct synthetic playtesters and demonstrates how generative player models can be applied to a varied corpus of game levels and how different playstyles can be enacted in each level.

Pharmacokinetics of a novel formulation of ivermectin after administration to goats

The commercial formulation used in this study is a good option to consider when administering ivermectin to goats because of the high absorption, which is characterized by high values of F.

Generating Behavior-Diverse Game AIs with Evolutionary Multi-Objective Deep Reinforcement Learning

Evaluations on the Atari and real commercial games indicate that, compared to existing algorithms, EMOGI performs better in generating diverse behaviors and significantly improves the efficiency of Game AI design.

Benchmarking End-to-End Behavioural Cloning on Video Games

The results show that these agents cannot match humans in raw performance but do learn basic dynamics and rules, and it is demonstrated how the quality of the data matters, and how recording data from humans is subject to a state-action mismatch, due to human reflexes.

Data-Driven, Data-Informed, Data-Augmented: How Ubisoft’s Ghost Recon Wildlands Live Unit Uses Data for Continuous Product Innovation

A unit at Ubisoft, a leading game publisher headquartered in Paris, has established a three-pronged approach to drive product innovation based on three practices: data-driven exploration, data-augmented ideation, and data-informed validation.

Playing Styles in StarCraft

Extending Reinforcement Learning to Provide Dynamic Game Balancing

This work presents an innovative use of reinforcement learning to build intelligent agents that adapt their behavior in order to provide dynamic game balancing, and applies it to a real-time fighting game, obtaining good results.

Like a DNA String: Sequence-Based Player Profiling in Tom Clancy's The Division

The approach presented provides a mixed-methods framework, combining qualitative knowledge elicitation and workshops with largescale telemetry analysis, using sequence mining and clustering to develop detailed player profiles showing the core gameplay loops of The Division’s players.