More Like this

1. Principled Reinforcement Learning with Human Feedback from Pairwise or K-wise Comparisons

   Zhu, Banghua and (January 2023, Proceedings of Machine Learning Research)

   Krause, Andreas and (Ed.)

   We provide a theoretical framework for Reinforcement Learning with Human Feedback (RLHF). We show that when the underlying true reward is linear, under both Bradley-Terry-Luce (BTL) model (pairwise comparison) and Plackett-Luce (PL) model ($$K$$-wise comparison), MLE converges under certain semi-norm for the family of linear reward. On the other hand, when training a policy based on the learned reward model, we show that MLE fails while a pessimistic MLE provides policies with good performance under certain coverage assumption. We also show that under the PL model, both the true MLE and a different MLE which splits the $$K$$-wise comparison into pairwise comparisons converge, while the true MLE is asymptotically more efficient. Our results validate the empirical success of the existing RLHF algorithms, and provide new insights for algorithm design. Our analysis can also be applied for the problem of online RLHF and inverse reinforcement learning. 

   more » « less
2. Policy Gradient Bayesian Robust Optimization for Imitation Learning

   Javed, Zaynah; Brown, Daniel; Sharma, Satvik; Zhu, Jerry; Balakrishna, Ashwin; Petrik, Marek; Dragan, Anca; Goldberg, Ken (January 2021, 38th International Conference on Machine Learning)

   The difficulty in specifying rewards for many real world problems has led to an increased focus on learning rewards from human feedback, such as demonstrations. However, there are often many different reward functions that explain the human feedback, leaving agents with uncertainty over what the true reward function is. While most policy optimization approaches handle this uncertainty by optimizing for expected performance, many applications demand risk-averse behavior. We derive a novel policy gradient-style robust optimization approach, PG-BROIL, that optimizes a soft-robust objective that balances expected performance and risk. To the best of our knowledge, PG-BROIL is the first policy optimization algorithm robust to a distribution of reward hypotheses which can scale to continuous MDPs. Results suggest that PG-BROIL can produce a family of behaviors ranging from risk-neutral to risk-averse and outperforms state-of-the-art imitation learning algorithms when learning from ambiguous demonstrations by hedging against uncertainty, rather than seeking to uniquely identify the demonstrator’s reward function. 

   more » « less
3. MPO: An Efficient Post-Processing Framework for Mixing Diverse Preference Alignment

   Wang, T; Gui, D; Hu, Y; Lin, S; Zhang, L (July 2025, Proceedings of Machine Learning Research)

   Reinforcement Learning from Human Feedback (RLHF) has shown promise in aligning large language models (LLMs). Yet its reliance on a singular reward model often overlooks the diversity of human preferences. Recent approaches address this limitation by leveraging multi-dimensional feedback to fine-tune corresponding reward models and train LLMs using reinforcement learning. However, the process is costly and unstable, especially given the competing and heterogeneous nature of human preferences. In this paper, we propose Mixing Preference Optimization (MPO), a post-processing framework for aggregating single-objective policies as an alternative to both multi-objective RLHF (MORLHF) and MaxMin-RLHF. MPO avoids alignment from scratch. Instead, it log-linearly combines existing policies into a unified one with the weight of each policy computed via a batch stochastic mirror descent. Empirical results demonstrate that MPO achieves balanced performance across diverse preferences, outperforming or matching existing models with significantly reduced computational costs. 

   more » « less
4. Can Differentiable Decision Trees Enable Interpretable Reward Learning from Human Feedback?

   Kalra, Akansha; Brown, Daniel S (August 2024, Reinforcement Learning Journal (RLJ))

   Reinforcement Learning from Human Feedback (RLHF) has emerged as a popular paradigm for capturing human intent to alleviate the challenges of hand-crafting the reward values. Despite the increasing interest in RLHF, most works learn black box reward functions that while expressive are difficult to interpret and often require running the whole costly process of RL before we can even decipher if these frameworks are actually aligned with human preferences. We propose and evaluate a novel approach for learning expressive and interpretable reward functions from preferences using Differentiable Decision Trees (DDTs). Our experiments across several domains, including CartPole, Visual Gridworld environments and Atari games, provide evidence that the tree structure of our learned reward function is useful in determining the extent to which the reward function is aligned with human preferences. We also provide experimental evidence that not only shows that reward DDTs can often achieve competitive RL performance when compared with larger capacity deep neural network reward functions but also demonstrates the diagnostic utility of our framework in checking alignment of learned reward functions. We also observe that the choice between soft and hard (argmax) output of reward DDT reveals a tension between wanting highly shaped rewards to ensure good RL performance, while also wanting simpler, more interpretable rewards. Videos and code, are available at: https://sites.google.com/view/ddt-rlhf 

   more » « less
5. Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning

   Poddar, Sriyash; Wan, Yanming; Ivison, Hamish; Gupta, Abhishek; Jaques, Natasha (December 2024, Neural Information Processing Systems 2024)

   Reinforcement Learning from Human Feedback (RLHF) is a powerful paradigm for aligning foundation models to human values and preferences. However, current RLHF techniques cannot account for the naturally occurring differences in individual human preferences across a diverse population. When these differences arise, traditional RLHF frameworks simply average over them, leading to inaccurate rewards and poor performance for individual subgroups. To address the need for pluralistic alignment, we develop a class of multimodal RLHF methods. Our proposed techniques are based on a latent variable formulation - inferring a novel user-specific latent and learning reward models and policies conditioned on this latent without additional user-specific data. While conceptually simple, we show that in practice, this reward modeling requires careful algorithmic considerations around model architecture and reward scaling. To empirically validate our proposed technique, we first show that it can provide a way to combat under- specification in simulated control problems, inferring and optimizing user-specific reward functions. Next, we conduct experiments on pluralistic language datasets representing diverse user preferences and demonstrate improved reward function accuracy. We additionally show the benefits of this probabilistic framework in terms of measuring uncertainty, and actively learning user preferences. This work enables learning from diverse populations of users with divergent preferences, an important challenge that naturally occurs in problems from robot learning to foundation model alignment. 

   more » « less