Tang, Xiaohang;
Marques, Afonso;
Kamalaruban, Parameswaran;
Bogunovic, Ilija;
(2024)
Adversarial Robust Decision Transformer.
In:
Proceeding of the 38th Annual Conference on Neural Information Processing Systems.
(pp. pp. 1-26).
NeurIPS
(In press).
Preview |
Text
Tang_Adversarial Robust Decision Transformer_AOP.pdf Download (902kB) | Preview |
Abstract
Decision Transformer (DT), as one of the representative Reinforcement Learning via Supervised Learning (RvS) methods, has achieved strong performance in offline learning tasks by leveraging the powerful Transformer architecture for sequential decision-making. However, in adversarial environments, these methods can be non-robust, since the return is dependent on the strategies of both the decisionmaker and adversary. Training a probabilistic model conditioned on observed return to predict action can fail to generalize, as the trajectories that achieve a return in the dataset might have done so due to a suboptimal behavior adversary. To address this, we propose a worst-case-aware RvS algorithm, the Adversarially Robust Decision Transformer (ARDT), which learns and conditions the policy on in-sample minimax returns-to-go. ARDT aligns the target return with the worst-case return learned through minimax expectile regression, thereby enhancing robustness against powerful test-time adversaries. In experiments conducted on sequential games with full data coverage, ARDT can generate a maximin (Nash Equilibrium) strategy, the solution with the largest adversarial robustness. In large-scale sequential games and continuous adversarial RL environments with partial data coverage, ARDT demonstrates significantly superior robustness to powerful test-time adversaries and attains higher worst-case returns compared to contemporary DT methods.
| Type: | Proceedings paper |
|---|---|
| Title: | Adversarial Robust Decision Transformer |
| Event: | 38th Annual Conference on Neural Information Processing Systems |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | https://openreview.net/pdf?id=WEf2LT8NtY |
| Language: | English |
| Additional information: | © The Authors 2024. Original content in this paper is licensed under the terms of the Creative Commons Attribution 4.0 International (CC BY 4.0) Licence (https://creativecommons.org/licenses/by/4.0/). |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Electronic and Electrical Eng |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10202581 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
