Choreographer: Learning and Adapting Skills in Imagination
Dec 2, 2022
Speakers
Pietro Mazzaglia
Speaker · 0 followers
Tim Verbelen
Speaker · 0 followers
Bart Dhoedt
Speaker · 0 followers
Alexandre Lacoste
Speaker · 0 followers
Sai Rajeswar
Speaker · 0 followers
About
Unsupervised skill learning aims to learn a rich repertoire of behaviors without external supervision, providing artificial agents with the ability to control and influence the environment. However, without appropriate knowledge and exploration, skills may provide control only over a restricted area of the environment, limiting their applicability. Furthermore, it is unclear how to leverage the learned skill behaviors for adapting to downstream tasks in a data-efficient manner. We present Choreographer, a model-based agent that exploits its world model to learn and adapt skills in imagination. Our method decouples the exploration and skill learning processes, being able to discover skills in the latent state space of the model. During adaptation, the agent uses a meta-controller to evaluate and adapt the learned skills efficiently by deploying them in parallel in imagination. Choreographer is able to learn skills both from offline data, and by collecting data simultaneously with an exploration policy. The skills can be used to effectively adapt to downstream tasks, as we show in the URL benchmark, where we outperform previous approaches from both pixels and states inputs. The skills also explore the environment thoroughly, finding sparse rewards more frequently, as shown in goal-reaching tasks from the DMC Suite and Meta-World. Project website: https://doubleblind-repos.github.io/Unsupervised skill learning aims to learn a rich repertoire of behaviors without external supervision, providing artificial agents with the ability to control and influence the environment. However, without appropriate knowledge and exploration, skills may provide control only over a restricted area of the environment, limiting their applicability. Furthermore, it is unclear how to leverage the learned skill behaviors for adapting to downstream tasks in a data-efficient manner. We present Chore…
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
Listen to Interpret: Post-hoc Interpretability for Audio Networks with NMF
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Look Around and Refer: 2D Synthetic Semantics Knowledge Distillation for 3D Visual Grounding
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
KSD Aggregated Goodness-of-fit Test
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Implementing Reinforcement Learning Datacenter Congestion Control in NVIDIA NICs
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
CabiNet: Scaling Neural Collision Detection for Object Rearrangement with Procedural Scene Generation
Watch later
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%