RLUC: Strengthening robustness by attaching constraint considerations to policy network

J Tang, Q Liu, F Li, F Zhu - Expert Systems with Applications, 2024 - Elsevier
Deep reinforcement learning is widely used in many fields. However, recent research has
found vulnerabilities in agents trained by reinforcement learning algorithms and raised …

Self-adaptive imitation learning: Learning tasks with delayed rewards from sub-optimal demonstrations

Z Zhu, K Lin, B Dai, J Zhou - Proceedings of the AAAI conference on …, 2022 - ojs.aaai.org
Reinforcement learning (RL) has demonstrated its superiority in solving sequential decision-
making problems. However, heavy dependence on immediate reward feedback impedes …

Situation-Dependent Causal Influence-Based Cooperative Multi-Agent Reinforcement Learning

X Du, Y Ye, P Zhang, Y Yang, M Chen… - Proceedings of the AAAI …, 2024 - ojs.aaai.org
Learning to collaborate has witnessed significant progress in multi-agent reinforcement
learning (MARL). However, promoting coordination among agents and enhancing …

Phoebe: Reuse-aware online caching with reinforcement learning for emerging storage models

N Wu, P Li - arxiv preprint arxiv:2011.07160, 2020 - arxiv.org
With data durability, high access speed, low power efficiency and byte addressability, NVMe
and SSD, which are acknowledged representatives of emerging storage technologies, have …

A Simple Way to Incorporate Novelty Detection in World Models

G Zollicoffer, K Eaton, J Balloch, J Kim… - arxiv preprint arxiv …, 2023 - arxiv.org
Reinforcement learning (RL) using world models has found significant recent successes.
However, when a sudden change to world mechanics or properties occurs then agent …

A novel mountain driving unity simulated environment for autonomous vehicles

X Li, Z Cao, Q Bai - Proceedings of the AAAI Conference on Artificial …, 2021 - ojs.aaai.org
The simulated driving environment provides a low cost and time-saving platform to test the
performance of the autonomous vehicle by linkage with existing machine learning …

User-oriented robust reinforcement learning

H You, B Yu, H **, Z Yang, J Sun - … of the AAAI Conference on Artificial …, 2023 - ojs.aaai.org
Recently, improving the robustness of policies across different environments attracts
increasing attention in the reinforcement learning (RL) community. Existing robust RL …

[CITAZIONE][C] Online learning in non-cooperative configurable Markov decision process

G Ramponi, AM Metelli, A Concetti, M Restelli - AAAI-21 Workshop on Reinforcement …, 2021