Learning Representations in Video Game Agents with Supervised Contrastive Imitation Learning
This paper introduces a novel application of Supervised Contrastive Learning (SupCon) to Imitation Learning (IL), with a focus on learning more effective state representations for agents in video game environments. The goal is to obtain latent representations of the observations that capture better the action-relevant factors, thereby modeling better the cause-effect relationship from the observations that are mapped to the actions performed by the demonstrator, for example, the player jumps whenever an obstacle appears ahead. We propose an approach to integrate the SupCon loss with continuous output spaces, enabling SupCon to operate without constraints regarding the type of actions of the environment. Experiments on the 3D games Astro Bot and Returnal, and multiple 2D Atari games show improved representation quality, faster learning convergence, and better generalization compared to baseline models trained only with supervised action prediction loss functions.
Code (0)
등록된 구현이 없습니다.
Tasks
Contrastive LearningAtari GamesSimilar Papers 제목 키워드 기반
Contrastive Learning of Generalized Game Representations
Representing games through their pixels offers a promising approach for building general-purpose and versatile game models. While games are not merely images, neural network models trained on game pixels often capture di…
Contrastive LearningImage ClassificationRepresentation LearningG2L: Semantically Aligned and Uniform Video Grounding via Geodesic and Game Theory
The recent video grounding works attempt to introduce vanilla contrastive learning into video grounding. However, we claim that this naive solution is suboptimal. Contrastive learning requires two key properties: (1) \em…
Contrastive LearningVideo GroundingAn Unsupervised Video Game Playstyle Metric via State Discretization
On playing video games, different players usually have their own playstyles. Recently, there have been great improvements for the video game AIs on the playing strength. However, past researches for analyzing the behavio…
Atari GamesCar RacingDecision MakingLearning Self-Supervised Audio-Visual Representations for Sound Recommendations
We propose a novel self-supervised approach for learning audio and visual representations from unlabeled videos, based on their correspondence. The approach uses an attention mechanism to learn the relative importance of…
Contrastive LearningContrastive Learning for Sports Video: Unsupervised Player Classification
We address the problem of unsupervised classification of players in a team sport according to their team affiliation, when jersey colours and design are not known a priori. We adopt a contrastive learning approach in whi…
ClassificationContrastive LearningGeneral Classification