Sep 17, 2021 · Abstract:In real scenarios, state observations that an agent observes may contain measurement errors or adversarial noises, misleading the ...

Sep 18, 2023 · In this paper, we study the training robustness of distributional Reinforcement Learning (RL), a class of state-of-the-art methods that estimate the whole ...

Sep 9, 2024 · In this paper, we study the training robustness of distributional Reinforcement Learning~(RL), a class of state-of-the-art methods that estimate ...

However, distributional RL can enjoys better training robustness in the more complicated noisy state observation settings compared with its expectation- based ...

Study of the training robustness of distributional Reinforcement Learning, a class of state-of-the-art methods that estimate the whole distribution of the ...

Official implementation of 'Exploring the Training Robustness of Distributional Reinforcement Learning against Noisy State Observations' (ECML-PKDD 2023).

Sep 18, 2023 · In this paper, we study the training robustness of distributional Reinforcement Learning (RL), a class of state-of-the-art methods that estimate the whole ...

The resulting stable gradients while the optimization in distributional RL accounts for its better training robustness against state observation noises. Finally ...

Exploring the Training Robustness of Distributional Reinforcement Learning Against Noisy State Observations. https://doi.org/10.1007/978-3-031-43424-2_3 ·.