paper-with-me

홈 › Papers

Rethinking Inverse Reinforcement Learning: from Data Alignment to Task Alignment

2024-10-31 · Weichao Zhou, Wenchao Li

Many imitation learning (IL) algorithms use inverse reinforcement learning (IRL) to infer a reward function that aligns with the demonstration. However, the inferred reward functions often fail to capture the underlying task objectives. In this paper, we propose a novel framework for IRL-based IL that prioritizes task alignment over conventional data alignment. Our framework is a semi-supervised approach that leverages expert demonstrations as weak supervision to derive a set of candidate reward functions that align with the task rather than only with the data. It then adopts an adversarial mechanism to train a policy with this set of reward functions to gain a collective validation of the policy's ability to accomplish the task. We provide theoretical insights into this framework's ability to mitigate task-reward misalignment and present a practical implementation. Our experimental results show that our framework outperforms conventional IL baselines in complex and transfer learning scenarios.

📄 PDF Abstract BibTeX arXiv:2410.23680

Code (1)

zwc662/PAGAR 공식 구현 pytorch

Tasks

Imitation LearningTransfer Learning

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…
SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Rethinking Loss Reweighting for Imbalance Learning as an Inverse Problem: A Neural Collapse Point of View

2026-05-11 · Jinping Wang, Zixin Tong, Zhiwu Xie, Zhiqiang Gao arxiv

Loss reweighting is a widely used strategy for long-tailed classification, but existing reweighting strategies often rely on heuristics and rarely define a well-specified target. Inspired by Neural Collapse (NC), the ide…

PAGAR: Taming Reward Misalignment in Inverse Reinforcement Learning-Based Imitation Learning with Protagonist Antagonist Guided Adversarial Reward

2023-06-02 · Weichao Zhou, Wenchao Li

Many imitation learning (IL) algorithms employ inverse reinforcement learning (IRL) to infer the intrinsic reward function that an expert is implicitly optimizing for based on their demonstrated behaviors. However, in pr…

Imitation LearningZero-Shot Learning

Interactionless Inverse Reinforcement Learning: A Data-Centric Framework for Durable Alignment

2026-02-16 · Elias Malomgré, Pieter Simoens arxiv

AI alignment is growing in importance, yet many current approaches learn safety behavior by directly modifying policy parameters, entangling normative constraints with the underlying policy. This often yields opaque, dif…

Reinforcement Learning

HAIR: Hardness-Aware Inverse Reinforcement Learning with Introspective Reasoning for LLM Alignment

2025-03-23 · Ruoxi Cheng, Haoxuan Ma, Weixin Wang

The alignment of large language models (LLMs) with human values remains critical yet hindered by four key challenges: (1) scarcity of balanced safety datasets, (2) alignment tax, (3) vulnerability to jailbreak attacks du…

Multi Task Inverse Reinforcement Learning for Common Sense Reward

2024-02-17 · Neta Glazer, Aviv Navon, Aviv Shamsian, Ethan Fetaya

One of the challenges in applying reinforcement learning in a complex real-world environment lies in providing the agent with a sufficiently detailed reward function. Any misalignment between the reward and the desired b…

Common Sense Reasoningreinforcement-learningReinforcement Learning