ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters

Peng, Xue Bin; Guo, Yunrong; Halper, Lina; Levine, Sergey; Fidler, Sanja

doi:10.48550/arxiv.2205.01906

Cited by 4 publications

(5 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [112] and [113], the reward is defined as the distance to the goal in the learned latent space, where the goal is chosen as the final state in the demonstration trajectory. Recent works on motion imitation [114]- [116] carefully design the reward as a weighted distance to the reference state, taking joint orientations, joint velocities, end effectors, and centers of mass into account.…”

Section: Demo As Reference For Rewardmentioning

confidence: 99%

Boosting Reinforcement Learning and Planning with Demonstrations: A Survey

Mu¹,

Sheng²

2023

Preprint

View full text Add to dashboard Cite

Although reinforcement learning has seen tremendous success recently, this kind of trial-and-error learning can be impractical or inefficient in complex environments. The use of demonstrations, on the other hand, enables agents to benefit from expert knowledge rather than having to discover the best action to take through exploration. In this survey, we discuss the advantages of using demonstrations in sequential decision making, various ways to apply demonstrations in learning-based decision making paradigms (for example, reinforcement learning and planning in the learned models), and how to collect the demonstrations in various scenarios. Additionally, we exemplify a practical pipeline for generating and utilizing demonstrations in the recently proposed ManiSkill robot learning benchmark.

show abstract

Section: Demo As Reference For Rewardmentioning

confidence: 99%

Boosting Reinforcement Learning and Planning with Demonstrations: A Survey

Mu¹,

Sheng²

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Similar to AMP, Adversarial Skill Embedding (ASE) [4] also adapted discriminator. However, unlike AMP, ASE proposed two stages: a pre-training stage for low-level policy which is conditioned by state and embedded skills, and a transferring embedded skills stage for high-level policy.…”

Section: Gan In Character Animationmentioning

confidence: 99%

“…To cooperate interactions without explicit programming, Generative Adversarial Imitation Learning [2] is an alternative to imitation learning. Adversarial Motion Prior [3] and Adversarial Skill Embeddings [4] are two notable approaches that apply generative adversarial imitation learning to the field of character animation and have shown remarkable results in generating natural motions. From the perspective of a generative model, these two models leverage Generative Adversarial Networks to provide information on the fake distribution.…”

Section: Introductionmentioning

confidence: 99%

캐릭터 복싱 과제에서 Gan 기반 접근법과 강화학습의 효과성 탐구

Son,

Kwon

2023

J Korea Comput Graph Soc

View full text Add to dashboard Cite

For decades, creating a desired locomotive motion in a goal-oriented manner has been a challenge in character animation. Datadriven methods using generative models have demonstrated efficient ways of predicting long sequences of motions without the need for explicit conditioning. While these methods produce high-quality long-term motions, they can be limited when it comes to synthesizing motion for challenging novel scenarios, such as punching a random target. A state-of-the-art solution to overcome this limitation is by using a GAN Discriminator to imitate motion data clips and incorporating reinforcement learning to compose goaloriented motions. In this paper, our research aims to create characters performing combat sports such as boxing, using a novel reward design in conjunction with existing GAN-based approaches. We experimentally demonstrate that both the Adversarial Motion Prior [3] and Adversarial Skill Embeddings [4] methods are capable of generating viable motions for a character punching a random target, even in the absence of mocap data that specifically captures the transition between punching and locomotion. Also, with a single learned policy, multiple task controllers can be constructed through the TimeChamber framework.

show abstract

“…Robots also struggle to generalize or adapt to other environments or tasks. To alleviate this problem to a certain extent, there have been recent DRL studies based on motion priors [86][87][88][89][90] , which have been successfully applied to quadrupedal locomotion tasks [12,56,91] . However, the variety of motion priors in these studies is insufficient, and the robot' s behavior is not agile and natural.…”

Section: Reuse Of Motion Priors Datamentioning

confidence: 99%

Deep reinforcement learning for real-world quadrupedal locomotion: a comprehensive review

Zhang¹,

Li²,

Wang³

2022

Intell Robot

View full text Add to dashboard Cite

Building controllers for legged robots with agility and intelligence has been one of the typical challenges in the pursuit of artificial intelligence (AI). As an important part of the AI field, deep reinforcement learning (DRL) can realize sequential decision making without physical modeling through end-to-end learning and has achieved a series of major breakthroughs in quadrupedal locomotion research. In this review article, we systematically organize and summarize relevant important literature, covering DRL algorithms from problem setting to advanced learning methods. These algorithms alleviate the specific problems encountered in the practical application of robots to a certain extent. We first elaborate on the general development trend in this field from several aspects, such as the DRL algorithms, simulation environments, and hardware platforms. Moreover, core components in the algorithm design, such as state and action spaces, reward functions, and solutions to reality gap problems, are highlighted and summarized. We further discuss open problems and propose promising future research directions to discover new areas of research.

show abstract

ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters

Abstract: embedding then enables the character to automatically synthesize complex and naturalistic strategies in order to achieve the task objectives. CCS Concepts: • Computing methodologies → Procedural animation; Control methods; Adversarial learning.

Cited by 4 publications

References 47 publications

Boosting Reinforcement Learning and Planning with Demonstrations: A Survey

Boosting Reinforcement Learning and Planning with Demonstrations: A Survey

캐릭터 복싱 과제에서 Gan 기반 접근법과 강화학습의 효과성 탐구

Deep reinforcement learning for real-world quadrupedal locomotion: a comprehensive review

Contact Info

Product

Resources

About