Self-Improving Robust Preference Optimization
- URL: http://arxiv.org/abs/2406.01660v3
- Date: Fri, 7 Jun 2024 17:25:12 GMT
- Title: Self-Improving Robust Preference Optimization
- Authors: Eugene Choi, Arash Ahmadian, Matthieu Geist, Oilvier Pietquin, Mohammad Gheshlaghi Azar,
- Abstract summary: Self-Improving Robust Preference Optimization SRPO is a practical and mathematically principled offline RLHF framework.
In particular, when SRPO is evaluated on the OOD XSUM dataset, it outperforms the celebrated DPO by a clear margin of 15% after 5 self-revisions.
- Score: 22.493029742076605
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Both online and offline RLHF methods such as PPO and DPO have been extremely successful in aligning AI with human preferences. Despite their success, the existing methods suffer from a fundamental problem that their optimal solution is highly task-dependent (i.e., not robust to out-of-distribution (OOD) tasks). Here we address this challenge by proposing Self-Improving Robust Preference Optimization SRPO, a practical and mathematically principled offline RLHF framework that is completely robust to the changes in the task. The key idea of SRPO is to cast the problem of learning from human preferences as a self-improvement process, which can be mathematically expressed in terms of a min-max objective that aims at joint optimization of self-improvement policy and the generative policy in an adversarial fashion. The solution for this optimization problem is independent of the training task and thus it is robust to its changes. We then show that this objective can be re-expressed in the form of a non-adversarial offline loss which can be optimized using standard supervised optimization techniques at scale without any need for reward model and online inference. We show the effectiveness of SRPO in terms of AI Win-Rate (WR) against human (GOLD) completions. In particular, when SRPO is evaluated on the OOD XSUM dataset, it outperforms the celebrated DPO by a clear margin of 15% after 5 self-revisions, achieving WR of 90%.
Related papers
- Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization [78.82586283794886]
We present a new offline alignment algorithm, $chi2$-Preference Optimization ($chi$PO)
$chi$PO implements the principle of pessimism in the face of uncertainty via regularization.
It is provably robust to overoptimization and achieves sample-complexity guarantees based on single-policy concentrability.
arXiv Detail & Related papers (2024-07-18T11:08:40Z) - Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer [52.09480867526656]
We identify the source of misalignment as a form of distributional shift and uncertainty in learning human preferences.
To mitigate overoptimization, we first propose a theoretical algorithm that chooses the best policy for an adversarially chosen reward model.
Using the equivalence between reward models and the corresponding optimal policy, the algorithm features a simple objective that combines a preference optimization loss and a supervised learning loss.
arXiv Detail & Related papers (2024-05-26T05:38:50Z) - Overcoming Reward Overoptimization via Adversarial Policy Optimization with Lightweight Uncertainty Estimation [46.61909578101735]
Adversarial Policy Optimization (AdvPO) is a novel solution to the pervasive issue of reward over-optimization in Reinforcement Learning from Human Feedback.
In this paper, we introduce a lightweight way to quantify uncertainties in rewards, relying solely on the last layer embeddings of the reward model.
arXiv Detail & Related papers (2024-03-08T09:20:12Z) - Towards Efficient Exact Optimization of Language Model Alignment [93.39181634597877]
Direct preference optimization (DPO) was proposed to directly optimize the policy from preference data.
We show that DPO derived based on the optimal solution of problem leads to a compromised mean-seeking approximation of the optimal solution in practice.
We propose efficient exact optimization (EXO) of the alignment objective.
arXiv Detail & Related papers (2024-02-01T18:51:54Z) - Preference as Reward, Maximum Preference Optimization with Importance Sampling [3.7040071165219595]
We propose a simple and intuitive off-policy preference optimization algorithm from an importance sampling view, which we call Maximum Preference Optimization (MPO)
MPO achieves the best of both worlds by combining the objectives of RLHF and IPO while being an off-policy algorithm.
arXiv Detail & Related papers (2023-12-27T06:34:54Z) - REBEL: A Regularization-Based Solution for Reward Overoptimization in Robotic Reinforcement Learning from Human Feedback [61.54791065013767]
A misalignment between the reward function and user intentions, values, or social norms can be catastrophic in the real world.
Current methods to mitigate this misalignment work by learning reward functions from human preferences.
We propose a novel concept of reward regularization within the robotic RLHF framework.
arXiv Detail & Related papers (2023-12-22T04:56:37Z) - OptiDICE: Offline Policy Optimization via Stationary Distribution
Correction Estimation [59.469401906712555]
We present an offline reinforcement learning algorithm that prevents overestimation in a more principled way.
Our algorithm, OptiDICE, directly estimates the stationary distribution corrections of the optimal policy.
We show that OptiDICE performs competitively with the state-of-the-art methods.
arXiv Detail & Related papers (2021-06-21T00:43:30Z)
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.