Skip to Main content Skip to Navigation
Conference papers

Only Relevant Information Matters: Filtering Out Noisy Samples to Boost RL

Yannis Flet-Berliac 1, 2, 3 Philippe Preux 1, 2, 3
1 SEQUEL - Sequential Learning
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
Abstract : In reinforcement learning, policy gradient algorithms optimize the policy directly and rely on sampling efficiently an environment. Nevertheless, while most sampling procedures are based on direct policy sampling, self-performance measures could be used to improve such sampling prior to each policy update. Following this line of thought, we introduce SAUNA, a method where non-informative transitions are rejected from the gradient update. The level of information is estimated according to the fraction of variance explained by the value function: a measure of the discrepancy between V and the empirical returns. In this work, we use this metric to select samples that are useful to learn from, and we demonstrate that this selection can significantly improve the performance of policy gradient methods. In this paper: (a) We define SAUNA's metric and introduce its method to filter transitions. (b) We conduct experiments on a set of benchmark continuous control problems. SAUNA significantly improves performance. (c) We investigate how SAUNA reliably selects samples with the most positive impact on learning and study its improvement on both performance and sample efficiency.
Complete list of metadatas

Cited literature [9 references]  Display  Hide  Download

https://hal.inria.fr/hal-02091547
Contributor : Yannis Flet-Berliac <>
Submitted on : Friday, November 20, 2020 - 4:58:52 PM
Last modification on : Friday, November 27, 2020 - 2:20:08 PM

File

sauna_ijcai_camera_ready.pdf
Files produced by the author(s)

Identifiers

Citation

Yannis Flet-Berliac, Philippe Preux. Only Relevant Information Matters: Filtering Out Noisy Samples to Boost RL. IJCAI 2020 - International Joint Conference on Artificial Intelligence, Jul 2020, Yokohama, Japan. ⟨10.24963/ijcai.2020/376⟩. ⟨hal-02091547v6⟩

Share

Metrics

Record views

15

Files downloads

18