Skip to Main content Skip to Navigation
Conference papers

HIGhER: Improving instruction following with Hindsight Generation for Experience Replay

Geoffrey Cideron 1 Mathieu Seurin 2 Florian Strub 3 Olivier Pietquin 4
2 Scool - Scool
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189
Abstract : Language creates a compact representation of the world and allows the description of unlimited situations and objectives through compositionality. While these characterizations may foster instructing, conditioning or structuring interactive agent behavior, it remains an open-problem to correctly relate language understanding and reinforcement learning in even simple instruction following scenarios. This joint learning problem is alleviated through expert demonstrations, auxiliary losses, or neural inductive biases. In this paper, we propose an orthogonal approach called Hindsight Generation for Experience Replay (HIGhER) that extends the Hindsight Experience Replay approach to the language-conditioned policy setting. Whenever the agent does not fulfill its instruction, HIGhER learns to output a new directive that matches the agent trajectory, and it relabels the episode with a positive reward. To do so, HIGhER learns to map a state into an instruction by using past successful trajectories, which removes the need to have external expert interventions to relabel episodes as in vanilla HER. We show the efficiency of our approach in the BabyAI environment, and demonstrate how it complements other instruction following methods.
Document type :
Conference papers
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03123981
Contributor : Mathieu Seurin Connect in order to contact the contributor
Submitted on : Thursday, January 28, 2021 - 12:10:19 PM
Last modification on : Friday, January 21, 2022 - 3:12:51 AM
Long-term archiving on: : Thursday, April 29, 2021 - 6:43:20 PM

File

HIGhER___ADPRL.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03123981, version 1

Citation

Geoffrey Cideron, Mathieu Seurin, Florian Strub, Olivier Pietquin. HIGhER: Improving instruction following with Hindsight Generation for Experience Replay. ADPRL 2020 - IEEE SSCI Conference on Adaptive Dynamic Programming and Reinforcement Learning, Dec 2020, Camberra / Virtual, Australia. ⟨hal-03123981⟩

Share

Metrics

Les métriques sont temporairement indisponibles