R Liu, F Bai, Y Du, Y Yang - Advances in Neural …, 2022 - proceedings.neurips.cc
Abstract Setting up a well-designed reward function has been challenging for many reinforcement learning applications. Preference-based reinforcement learning (PbRL) …
Reinforcement learning (RL) requires access to a reward function that incentivizes the right behavior, but these are notoriously hard to specify for complex tasks. Preference-based RL …
Conveying complex objectives to reinforcement learning (RL) agents can often be difficult, involving meticulous design of reward functions that are sufficiently informative yet easy …
Z Cao, KC Wong, CT Lin - IEEE Transactions on Neural …, 2021 - ieeexplore.ieee.org
The current reward learning from human preferences could be used to resolve complex reinforcement learning (RL) tasks without access to a reward function by defining a single …
X Liang, K Shu, K Lee, P Abbeel - arXiv preprint arXiv:2205.12401, 2022 - arxiv.org
Conveying complex objectives to reinforcement learning (RL) agents often requires meticulous reward engineering. Preference-based RL methods are able to learn a more …
Learning a reward function from human preferences is challenging as it typically requires having a high-fidelity simulator or using expensive and potentially unsafe actual physical …
Designing reward functions is a longstanding challenge in reinforcement learning (RL); it requires specialized knowledge or domain data, leading to high costs for development. To …
W Xue, B An, S Yan, Z Xu - arXiv preprint arXiv:2301.11774, 2023 - arxiv.org
The complexity of designing reward functions has been a major obstacle to the wide application of deep reinforcement learning (RL) techniques. Describing an agent's desired …
G An, J Lee, X Zuo, N Kosaka… - Advances in Neural …, 2023 - proceedings.neurips.cc
Preference-based reinforcement learning (PbRL) is an approach that enables RL agents to learn from preference, which is particularly useful when formulating a reward function is …