paper-with-me

Papers

Policy Improvement via Imitation of Multiple Oracles

2020-07-01 · NeurIPS 2020 12 · Ching-An Cheng, Andrey Kolobov, Alekh Agarwal

Despite its promise, reinforcement learning's real-world adoption has been hampered by the need for costly exploration to learn a good policy. Imitation learning (IL) mitigates this shortcoming by using an oracle policy during training as a bootstrap to accelerate the learning process. However, in many practical situations, the learner has access to multiple suboptimal oracles, which may provide conflicting advice in a state. The existing IL literature provides a limited treatment of such scenarios. Whereas in the single-oracle case, the return of the oracle's policy provides an obvious benchmark for the learner to compete against, neither such a benchmark nor principled ways of outperforming it are known for the multi-oracle setting. In this paper, we propose the state-wise maximum of the oracle policies' values as a natural baseline to resolve conflicting advice from multiple oracles. Using a reduction of policy optimization to online learning, we introduce a novel IL algorithm MAMBA, which can provably learn a policy competitive with this benchmark. In particular, MAMBA optimizes policies by using a gradient estimator in the style of generalized advantage estimation (GAE). Our theoretical analysis shows that this design makes MAMBA robust and enables it to outperform the oracle policies by a larger margin than the IL state of the art, even in the single-oracle case. In an evaluation against standard policy gradient with GAE and AggreVaTe(D), we showcase MAMBA's ability to leverage demonstrations both from a single and from multiple weak oracles, and significantly speed up policy optimization.

📄 PDF Abstract BibTeX arXiv:2007.00795

Code (0)

등록된 구현이 없습니다.

Tasks

Imitation LearningMamba

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Active Policy Improvement from Multiple Black-box Oracles

2023-06-17 · Xuefeng Liu, Takuma Yoneda, Chaoqi Wang, Matthew R. Walter 외

Reinforcement learning (RL) has made significant strides in various complex domains. However, identifying an effective policy via RL often necessitates extensive exploration. Imitation learning aims to mitigate this issu…

Imitation LearningReinforcement Learning (RL)

Blending Imitation and Reinforcement Learning for Robust Policy Improvement

2023-10-03 · Xuefeng Liu, Takuma Yoneda, Rick L. Stevens, Matthew R. Walter 외

While reinforcement learning (RL) has shown promising performance, its sample complexity continues to be a substantial hurdle, restricting its broader application across a variety of domains. Imitation learning (IL) util…

Imitation Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Contextual Bandits in Payment Processing: Non-uniform Exploration and Supervised Learning at Adyen

2024-11-30 · Akhila Vangara, Alex Egg

Uniform random exploration in decision-making systems supports off-policy learning via supervision but incurs high regret, making it impractical for many applications. Conversely, non-uniform exploration offers better im…

Multi-Armed Banditsregression

Global Policy-Space Response Oracles for Two-Player Zero-Sum Games

2026-05-27 · Junyu Zhang, Feihong Yang, Jian Wang, Chao Wang 외 arxiv

The Policy-Space Response Oracles (PSRO) framework scales equilibrium computation to large zero-sum games by iteratively expanding a restricted strategy set using deep reinforcement learning (DRL). A central challenge is…

Reinforcement Learning

Building Better Activation Oracles

2026-05-23 · Jan Bauer, Celeste De Schamphelaere, Adam Karvonen, Niclas Luick 외 arxiv

Activation Oracles (AOs) are promising methods for interpreting residual stream activations. However, current AOs face important issues, such as hallucinations and vagueness. Additionally, text-inversion confounds make t…