BLaDE: Robust Exploration via Diffusion Models
Dec 2, 2022
Speakers
Zhaohan Daniel Guo
Speaker · 0 followers
Shantanu Thakoor
Speaker · 0 followers
Bilal Piot
Speaker · 0 followers
Mohammad Gheshlaghi Azar
Speaker · 1 follower
About
We present Bootstrap your own Latents with Diffusion models for Exploration (BLaDE), a general approach for curiosity-driven exploration in complex, partially-observable and stochastic environments. BLaDE is a natural extension of Bootstrap Your Own Latents for Exploration (BYOL-Explore) which is a multi-step prediction-error method at the latent level that learns a world representation, the world dynamics, and provides an intrinsic-reward all-together by optimizing a single prediction loss with no additional auxiliary objective. Contrary to BYOL-Explore that predicts future latents from past latents and future open-loop actions, BLaDE predicts, via a diffusion model, future latents from past observations, future open-loop actions and a noisy version of future latents. Leaking information about future latents allows to obtain an intrinsic reward that does not depend on the variance of the distribution of future latents which makes the method agnostic to stochastic traps. Our experiments on different noisy versions of Montezuma's Revenge show that BLaDE handles stochasticity better than Random Network Distillation, Intrinsic Curiosity Module and BYOL-Explore without degrading the performance of BYOL-Explore in the non-noisy and fairly deterministicWe present Bootstrap your own Latents with Diffusion models for Exploration (BLaDE), a general approach for curiosity-driven exploration in complex, partially-observable and stochastic environments. BLaDE is a natural extension of Bootstrap Your Own Latents for Exploration (BYOL-Explore) which is a multi-step prediction-error method at the latent level that learns a world representation, the world dynamics, and provides an intrinsic-reward all-together by optimizing a single prediction loss with…
Organizer
NeurIPS 2022
Account · 961 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
BILCO: An Efficient Algorithm for Joint Alignment of Time Series
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
GAGA: Deciphering Age-path of Generalized Self-paced Regularizer
Watch later
Xingyu Qu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Exponential Family Model-Based Reinforcement Learning via Score Matching
Watch later
Gene Li, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Active Learning for Multiple Target Models
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Multi-Scale Adaptive Network for Single Image Denoising
Watch later
Yuanbiao Gou, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
CoupAlign: Coupling Word-Pixel with Sentence-Mask Alignments for Referring Image Segmentation
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%