Premium Only Content

AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control (Paper Explained)
#reiforcementlearning #gan #imitationlearning
Learning from demonstrations is a fascinating topic, but what if the demonstrations are not exactly the behaviors we want to learn? Can we adhere to a dataset of demonstrations and still achieve a specified goal? This paper uses GANs to combine goal-achieving reinforcement learning with imitation learning and learns to perform well at a given task while doing so in the style of a given presented dataset. The resulting behaviors include many realistic-looking transitions between the demonstrated movements.
OUTLINE:
0:00 - Intro & Overview
1:25 - Problem Statement
6:10 - Reward Signals
8:15 - Motion Prior from GAN
14:10 - Algorithm Overview
20:15 - Reward Engineering & Experimental Results
30:40 - Conclusion & Comments
Paper: https://arxiv.org/abs/2104.02180
Main Video: https://www.youtube.com/watch?v=wySUx...
Supplementary Video: https://www.youtube.com/watch?v=O6fBS...
Abstract:
Synthesizing graceful and life-like behaviors for physically simulated characters has been a fundamental challenge in computer animation. Data-driven methods that leverage motion tracking are a prominent class of techniques for producing high fidelity motions for a wide range of behaviors. However, the effectiveness of these tracking-based methods often hinges on carefully designed objective functions, and when applied to large and diverse motion datasets, these methods require significant additional machinery to select the appropriate motion for the character to track in a given scenario. In this work, we propose to obviate the need to manually design imitation objectives and mechanisms for motion selection by utilizing a fully automated approach based on adversarial imitation learning. High-level task objectives that the character should perform can be specified by relatively simple reward functions, while the low-level style of the character's behaviors can be specified by a dataset of unstructured motion clips, without any explicit clip selection or sequencing. These motion clips are used to train an adversarial motion prior, which specifies style-rewards for training the character through reinforcement learning (RL). The adversarial RL procedure automatically selects which motion to perform, dynamically interpolating and generalizing from the dataset. Our system produces high-quality motions that are comparable to those achieved by state-of-the-art tracking-based techniques, while also being able to easily accommodate large datasets of unstructured motion clips. Composition of disparate skills emerges automatically from the motion prior, without requiring a high-level motion planner or other task-specific annotations of the motion clips. We demonstrate the effectiveness of our framework on a diverse cast of complex simulated characters and a challenging suite of motor control tasks.
Authors: Xue Bin Peng, Ze Ma, Pieter Abbeel, Sergey Levine, Angjoo Kanazawa
Links:
TabNine Code Completion (Referral): http://bit.ly/tabnine-yannick
YouTube: https://www.youtube.com/c/yannickilcher
Twitter: https://twitter.com/ykilcher
Discord: https://discord.gg/4H8xxDF
BitChute: https://www.bitchute.com/channel/yann...
Minds: https://www.minds.com/ykilcher
Parler: https://parler.com/profile/YannicKilcher
LinkedIn: https://www.linkedin.com/in/ykilcher
BiliBili: https://space.bilibili.com/1824646584
If you want to support me, the best thing to do is to share out the content :)
If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this):
SubscribeStar: https://www.subscribestar.com/yannick...
Patreon: https://www.patreon.com/yannickilcher
Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq
Ethereum (ETH): 0x7ad3513E3B8f66799f507Aa7874b1B0eBC7F85e2
Litecoin (LTC): LQW2TRyKYetVC8WjFkhpPhtpbDM4Vw7r9m
Monero (XMR): 4ACL8AGrEo5hAir8A9CeVrW8pEauWvnp1WnSDZxW7tziCDLhZAGsgzhRQABDnFy8yuM9fWJDviJPHKRjV4FWt19CJZN9D4n
-
1:32
wavelanka
4 years agoSmart Motion Control Electric Screwdriver | World Top New Technologies | we love technology
92 -
37:44
Cashflow Ninja
4 years agoJayson Lowe Shares Why You Need To Control The Motion Of Money
41 -
6:58
UFAN
4 years ago $0.01 earnedPERPETUAL MOTION
107 -
1:45:36
Robert Gouveia
3 hours agoNew Jail Video 'Discrepancies' DISCOVERED! FBI Burn Bag! Biden Appointee FIRED!
27.6K4 -
15:18
T-SPLY
5 hours agoCNN DROPPED a NUKE On Democrats - Worst Polls Ever!
10.2K13 -
7:21
SKAP ATTACK
7 hours agoNBA Execs Think the Bubble Championship is a Joke
10.2K2 -
8:29
ARFCOM News
6 hours ago $0.51 earnedAG ~~REFUSES~~ To Stop Enforcing Unconstitutional Law | How Trump Plans To Give Guns Back To Felons
10.8K4 -
12:23:50
LFA TV
1 day agoLFA TV ALL DAY STREAM - FRIDAY 8/1/25
185K32 -
1:23:12
Roseanne Barr
4 hours agoBlackmail Nation: The Epstein Cover-Up with Nick Bryant | The Roseanne Barr Podcast #109
82.2K47 -
26:40
Michael Franzese
4 hours agoThe Self-Proclaimed King of the Mafia: Vito Genovese’s Fatal Throne
23.9K4