Reinforcement Learning from Human Feedback without Reward Inference: Model-Free Algorithm and Instance-Dependent Analysis

• URL: http://arxiv.org/abs/2406.07455v1
• Date: Tue, 11 Jun 2024 17:01:41 GMT
• Title: Reinforcement Learning from Human Feedback without Reward Inference: Model-Free Algorithm and Instance-Dependent Analysis
• Authors: Qining Zhang, Honghao Wei, Lei Ying,
• Abstract summary: We develop a model-free RLHF best policy identification algorithm, called $mathsfBSAD$, without explicit reward model inference. The algorithm identifies the optimal policy directly from human preference information in a backward manner.
• Score: 16.288866201806382
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we study reinforcement learning from human feedback (RLHF) under an episodic Markov decision process with a general trajectory-wise reward model. We developed a model-free RLHF best policy identification algorithm, called $\mathsf{BSAD}$, without explicit reward model inference, which is a critical intermediate step in the contemporary RLHF paradigms for training large language models (LLM). The algorithm identifies the optimal policy directly from human preference information in a backward manner, employing a dueling bandit sub-routine that constantly duels actions to identify the superior one. $\mathsf{BSAD}$ adopts a reward-free exploration and best-arm-identification-like adaptive stopping criteria to equalize the visitation among all states in the same decision step while moving to the previous step as soon as the optimal action is identifiable, leading to a provable, instance-dependent sample complexity $\tilde{\mathcal{O}}(c_{\mathcal{M}}SA^3H^3M\log\frac{1}{\delta})$ which resembles the result in classic RL, where $c_{\mathcal{M}}$ is the instance-dependent constant and $M$ is the batch size. Moreover, $\mathsf{BSAD}$ can be transformed into an explore-then-commit algorithm with logarithmic regret and generalized to discounted MDPs using a frame-based approach. Our results show: (i) sample-complexity-wise, RLHF is not significantly harder than classic RL and (ii) end-to-end RLHF may deliver improved performance by avoiding pitfalls in reward inferring such as overfit and distribution shift.

Related papers

• Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms [50.808123629394245]
  Reinforcement Learning from Human Feedback (RLHF) has been crucial to the recent success of Large Language Models (LLMs) This work formulates and formalizes the reward over-optimization or hacking problem for DAAs. We find that DAA methods deteriorate not only across a wide range of KL budgets but also often before even a single epoch of the dataset is completed.
  arXiv  Detail & Related papers  (2024-06-05T03:41:37Z)
• Improved Sample Complexity for Reward-free Reinforcement Learning under Low-rank MDPs [43.53286390357673]
  This paper focuses on reward-free reinforcement learning under low-rank MDP models. We first provide the first known sample complexity lower bound for any algorithm under low-rank MDPs. We then propose a novel model-based algorithm, coined RAFFLE, and show it can both find an $epsilon$-optimal policy and achieve an $epsilon$-accurate system identification.
  arXiv  Detail & Related papers  (2023-03-20T04:39:39Z)
• Model-Based Reinforcement Learning with Multinomial Logistic Function Approximation [12.36108042107798]
  We study model-based reinforcement learning for episodic Markov decision processes. We establish a provably efficient RL algorithm for the MDP whose state transition is given by a multinomial logistic model. We show that our proposed algorithm consistently outperforms the existing methods.
  arXiv  Detail & Related papers  (2022-12-27T16:25:09Z)
• Provably Efficient Offline Reinforcement Learning with Trajectory-Wise Reward [66.81579829897392]
  We propose a novel offline reinforcement learning algorithm called Pessimistic vAlue iteRaTion with rEward Decomposition (PARTED) PARTED decomposes the trajectory return into per-step proxy rewards via least-squares-based reward redistribution, and then performs pessimistic value based on the learned proxy reward. To the best of our knowledge, PARTED is the first offline RL algorithm that is provably efficient in general MDP with trajectory-wise reward.
  arXiv  Detail & Related papers  (2022-06-13T19:11:22Z)
• Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function Approximation [107.54516740713969]
  We study human-in-the-loop reinforcement learning (RL) with trajectory preferences. Instead of receiving a numeric reward at each step, the agent only receives preferences over trajectory pairs from a human overseer. We propose the first optimistic model-based algorithm for PbRL with general function approximation.
  arXiv  Detail & Related papers  (2022-05-23T09:03:24Z)
• Reward-Free RL is No Harder Than Reward-Aware RL in Linear Markov Decision Processes [61.11090361892306]
  Reward-free reinforcement learning (RL) considers the setting where the agent does not have access to a reward function during exploration. We show that this separation does not exist in the setting of linear MDPs. We develop a computationally efficient algorithm for reward-free RL in a $d$-dimensional linear MDP.
  arXiv  Detail & Related papers  (2022-01-26T22:09:59Z)
• Breaking the Sample Complexity Barrier to Regret-Optimal Model-Free Reinforcement Learning [52.76230802067506]
  A novel model-free algorithm is proposed to minimize regret in episodic reinforcement learning. The proposed algorithm employs an em early-settled reference update rule, with the aid of two Q-learning sequences. The design principle of our early-settled variance reduction method might be of independent interest to other RL settings.
  arXiv  Detail & Related papers  (2021-10-09T21:13:48Z)
• Model-based Reinforcement Learning for Continuous Control with Posterior Sampling [10.91557009257615]
  We study model-based posterior sampling for reinforcement learning (PSRL) in continuous state-action spaces. We present MPC-PSRL, a model-based posterior sampling algorithm with model predictive control for action selection.
  arXiv  Detail & Related papers  (2020-11-20T21:00:31Z)
• Model-Based Multi-Agent RL in Zero-Sum Markov Games with Near-Optimal Sample Complexity [67.02490430380415]
  We show that model-based MARL achieves a sample complexity of $tilde O(|S||B|(gamma)-3epsilon-2)$ for finding the Nash equilibrium (NE) value up to some $epsilon$ error. We also show that such a sample bound is minimax-optimal (up to logarithmic factors) if the algorithm is reward-agnostic, where the algorithm queries state transition samples without reward knowledge.
  arXiv  Detail & Related papers  (2020-07-15T03:25:24Z)

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.