A Unified Linear Programming Framework for Offline Reward Learning from Human Demonstrations and Feedback
- URL: http://arxiv.org/abs/2405.12421v2
- Date: Mon, 3 Jun 2024 23:23:54 GMT
- Title: A Unified Linear Programming Framework for Offline Reward Learning from Human Demonstrations and Feedback
- Authors: Kihyun Kim, Jiawei Zhang, Asuman Ozdaglar, Pablo A. Parrilo,
- Abstract summary: Inverse Reinforcement Learning (IRL) and Reinforcement Learning from Human Feedback (RLHF) are pivotal methodologies in reward learning.
This paper introduces a novel linear programming (LP) framework tailored for offline reward learning.
- Score: 6.578074497549894
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Inverse Reinforcement Learning (IRL) and Reinforcement Learning from Human Feedback (RLHF) are pivotal methodologies in reward learning, which involve inferring and shaping the underlying reward function of sequential decision-making problems based on observed human demonstrations and feedback. Most prior work in reward learning has relied on prior knowledge or assumptions about decision or preference models, potentially leading to robustness issues. In response, this paper introduces a novel linear programming (LP) framework tailored for offline reward learning. Utilizing pre-collected trajectories without online exploration, this framework estimates a feasible reward set from the primal-dual optimality conditions of a suitably designed LP, and offers an optimality guarantee with provable sample efficiency. Our LP framework also enables aligning the reward functions with human feedback, such as pairwise trajectory comparison data, while maintaining computational tractability and sample efficiency. We demonstrate that our framework potentially achieves better performance compared to the conventional maximum likelihood estimation (MLE) approach through analytical examples and numerical experiments.
Related papers
- Provably Efficient Interactive-Grounded Learning with Personalized Reward [44.64476717773815]
Interactive-Grounded Learning (IGL) is a powerful framework in which a learner aims at maximizing unobservable rewards.
We provide the first provably efficient algorithms with sublinear regret under realizability.
We propose two algorithms, one based on explore-then-exploit and the other based on inverse-gap weighting.
arXiv Detail & Related papers (2024-05-31T08:21:09Z) - Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment [65.15914284008973]
State-of-the-art techniques such as Reinforcement Learning from Human Feedback (RLHF) often consist of two stages.
1) supervised fine-tuning (SFT), where the model is fine-tuned by learning from human demonstration data.
2) Preference learning, where preference data is used to learn a reward model, which is in turn used by a reinforcement learning step to fine-tune the model.
arXiv Detail & Related papers (2024-05-28T07:11:05Z) - LIRE: listwise reward enhancement for preference alignment [27.50204023448716]
We propose a gradient-based reward optimization approach that incorporates the offline rewards of multiple responses into a streamlined listwise framework.
LIRE is straightforward to implement, requiring minimal parameter tuning, and seamlessly aligns with the pairwise paradigm.
Our experiments demonstrate that LIRE consistently outperforms existing methods across several benchmarks on dialogue and summarization tasks.
arXiv Detail & Related papers (2024-05-22T10:21:50Z) - Prior Constraints-based Reward Model Training for Aligning Large Language Models [58.33118716810208]
This paper proposes a Prior Constraints-based Reward Model (namely PCRM) training method to mitigate this problem.
PCRM incorporates prior constraints, specifically, length ratio and cosine similarity between outputs of each comparison pair, during reward model training to regulate optimization magnitude and control score margins.
Experimental results demonstrate that PCRM significantly improves alignment performance by effectively constraining reward score scaling.
arXiv Detail & Related papers (2024-04-01T07:49:11Z) - Sample Complexity of Preference-Based Nonparametric Off-Policy
Evaluation with Deep Networks [58.469818546042696]
We study the sample efficiency of OPE with human preference and establish a statistical guarantee for it.
By appropriately selecting the size of a ReLU network, we show that one can leverage any low-dimensional manifold structure in the Markov decision process.
arXiv Detail & Related papers (2023-10-16T16:27:06Z) - Provable Reward-Agnostic Preference-Based Reinforcement Learning [61.39541986848391]
Preference-based Reinforcement Learning (PbRL) is a paradigm in which an RL agent learns to optimize a task using pair-wise preference-based feedback over trajectories.
We propose a theoretical reward-agnostic PbRL framework where exploratory trajectories that enable accurate learning of hidden reward functions are acquired.
arXiv Detail & Related papers (2023-05-29T15:00:09Z) - Data Driven Reward Initialization for Preference based Reinforcement
Learning [20.13307800821161]
Preference-based Reinforcement Learning (PbRL) methods utilize binary feedback from the human in the loop (HiL) over queried trajectory pairs to learn a reward model.
We investigate the issue of a high degree of variability in the reward models which are sensitive to random seeds of the experiment.
arXiv Detail & Related papers (2023-02-17T07:07:07Z) - SURF: Semi-supervised Reward Learning with Data Augmentation for
Feedback-efficient Preference-based Reinforcement Learning [168.89470249446023]
We present SURF, a semi-supervised reward learning framework that utilizes a large amount of unlabeled samples with data augmentation.
In order to leverage unlabeled samples for reward learning, we infer pseudo-labels of the unlabeled samples based on the confidence of the preference predictor.
Our experiments demonstrate that our approach significantly improves the feedback-efficiency of the preference-based method on a variety of locomotion and robotic manipulation tasks.
arXiv Detail & Related papers (2022-03-18T16:50:38Z) - Learning from an Exploring Demonstrator: Optimal Reward Estimation for
Bandits [36.37578212532926]
We introduce the "inverse bandit" problem of estimating the rewards of a multi-armed bandit instance.
Existing approaches to the related problem of inverse reinforcement learning assume the execution of an optimal policy.
We develop simple and efficient reward estimation procedures for demonstrations within a class of upper-confidence-based algorithms.
arXiv Detail & Related papers (2021-06-28T17:37:49Z) - Provably Efficient Reward-Agnostic Navigation with Linear Value
Iteration [143.43658264904863]
We show how iteration under a more standard notion of low inherent Bellman error, typically employed in least-square value-style algorithms, can provide strong PAC guarantees on learning a near optimal value function.
We present a computationally tractable algorithm for the reward-free setting and show how it can be used to learn a near optimal policy for any (linear) reward function.
arXiv Detail & Related papers (2020-08-18T04:34:21Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.