Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization

• URL: http://arxiv.org/abs/2402.10342v2
• Date: Mon, 15 Jul 2024 04:19:50 GMT
• Title: Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization
• Authors: Yihan Du, Anna Winnicki, Gal Dalal, Shie Mannor, R. Srikant,
• Abstract summary: We consider an RLHF algorithm based on policy optimization (PO-RLHF) We provide performance bounds for PO-RLHF with low query complexity. Key novelty is a trajectory-level elliptical potential analysis.
• Score: 56.54271464134885
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement Learning from Human Feedback (RLHF) has achieved impressive empirical successes while relying on a small amount of human feedback. However, there is limited theoretical justification for this phenomenon. Additionally, most recent studies focus on value-based algorithms despite the recent empirical successes of policy-based algorithms. In this work, we consider an RLHF algorithm based on policy optimization (PO-RLHF). The algorithm is based on the popular Policy Cover-Policy Gradient (PC-PG) algorithm, which assumes knowledge of the reward function. In PO-RLHF, knowledge of the reward function is not assumed, and the algorithm uses trajectory-based comparison feedback to infer the reward function. We provide performance bounds for PO-RLHF with low query complexity, which provides insight into why a small amount of human feedback may be sufficient to achieve good performance with RLHF. A key novelty is a trajectory-level elliptical potential analysis, which bounds the reward estimation error when comparison feedback (rather than numerical reward observation) is given. We provide and analyze algorithms PG-RLHF and NN-PG-RLHF for two settings: linear and neural function approximation, respectively.

Related papers

• Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference [17.76565371753346]
  This paper develops two RLHF algorithms without reward inference. The key idea is to estimate the local value function difference from human preferences and then approximate the policy gradient with a zeroth-order gradient approximator. Our results show there exist provably efficient methods to solve general RLHF problems without reward inference.
  arXiv  Detail & Related papers  (2024-09-25T22:20:11Z)
• Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning [55.65738319966385]
  We propose a novel online algorithm, iterative Nash policy optimization (INPO) Unlike previous methods, INPO bypasses the need for estimating the expected win rate for individual responses. With an LLaMA-3-8B-based SFT model, INPO achieves a 42.6% length-controlled win rate on AlpacaEval 2.0 and a 37.8% win rate on Arena-Hard.
  arXiv  Detail & Related papers  (2024-06-30T08:00:34Z)
• The Effective Horizon Explains Deep RL Performance in Stochastic Environments [21.148001945560075]
  Reinforcement learning (RL) theory has largely focused on proving mini complexity sample bounds. We introduce a new RL algorithm, SQIRL, that iteratively learns a nearoptimal policy by exploring randomly to collect rollouts. We leverage SQIRL to derive instance-dependent sample complexity bounds for RL that are exponential only in an "effective horizon" look-ahead and on the complexity of the class used for approximation.
  arXiv  Detail & Related papers  (2023-12-13T18:58:56Z)
• Contrastive Preference Learning: Learning from Human Feedback without RL [71.77024922527642]
  We introduce Contrastive Preference Learning (CPL), an algorithm for learning optimal policies from preferences without learning reward functions. CPL is fully off-policy, uses only a simple contrastive objective, and can be applied to arbitrary MDPs.
  arXiv  Detail & Related papers  (2023-10-20T16:37:56Z)
• 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)
• Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO [90.90009491366273]
  We study the roots of algorithmic progress in deep policy gradient algorithms through a case study on two popular algorithms. Specifically, we investigate the consequences of "code-level optimizations:" Our results show that they (a) are responsible for most of PPO's gain in cumulative reward over TRPO, and (b) fundamentally change how RL methods function.
  arXiv  Detail & Related papers  (2020-05-25T16:24:59Z)

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.