| 1 |
Grounding Language to Autonomously-Acquired Skills via Goal Generation
|
|
|
|
In: ICLR 2021 - Ninth International Conference on Learning Representation ; https://hal.inria.fr/hal-03121146 ; ICLR 2021 - Ninth International Conference on Learning Representation, May 2021, Vienna / Virtual, Austria (2021)
|
|
Abstract:
International audience ; We are interested in the autonomous acquisition of repertoires of skills. Language-conditioned reinforcement learning (LC-RL) approaches are great tools in this quest, as they allow to express abstract goals as sets of constraints on the states. However, most LC-RL agents are not autonomous and cannot learn without external instructions and feedback. Besides, their direct language condition cannot account for the goal-directed behavior of pre-verbal infants and strongly limits the expression of behavioral diversity for a given language input. To resolve these issues, we propose a new conceptual approach to language-conditioned RL: the Language-Goal-Behavior architecture (LGB). LGB decouples skill learning and language grounding via an intermediate semantic representation of the world. To showcase the properties of LGB, we present a specific implementation called DECSTR. DECSTR is an intrinsically motivated learning agent endowed with an innate semantic representation describing spatial relations between physical objects. In a first stage (G -> B), it freely explores its environment and targets self-generated semantic configurations. In a second stage (L -> G), it trains a language-conditioned goal generator to generate semantic goals that match the constraints expressed in language-based inputs. We showcase the additional properties of LGB w.r.t. both an end-to-end LC-RL approach and a similar approach leveraging non-semantic, continuous intermediate representations. Intermediate semantic representations help satisfy language commands in a diversity of ways, enable strategy switching after a failure and facilitate language grounding.
|
|
Keyword:
[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]; [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG]; Artificial intelligence and robotics; Reinforcement learning
|
|
URL: https://hal.inria.fr/hal-03121146/file/2006.07185.pdf
https://hal.inria.fr/hal-03121146
https://hal.inria.fr/hal-03121146/document
|
|
BASE
|
|
Hide details
|
|
|
| 2 |
Language-Conditioned Goal Generation: a New Approach to Language Grounding in RL
|
|
|
|
In: https://hal.inria.fr/hal-03099887 ; 2021 (2021)
|
|
BASE
|
|
Show details
|
|
|
| 3 |
Language-Conditioned Goal Generation: a New Approach to Language Grounding for RL ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 4 |
Grounding Language to Autonomously-Acquired Skills via Goal Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|
|
