Direct Preference Optimization for Primitive-Enabled Hierarchical Reinforcement Learning

• URL: http://arxiv.org/abs/2411.00361v3
• Date: Mon, 25 Aug 2025 19:51:04 GMT
• Title: Direct Preference Optimization for Primitive-Enabled Hierarchical Reinforcement Learning
• Authors: Utsav Singh, Souradip Chakraborty, Wesley A. Suttle, Brian M. Sadler, Derrik E. Asher, Anit Kumar Sahu, Mubarak Shah, Vinay P. Namboodiri, Amrit Singh Bedi,
• Abstract summary: DIPPER is a novel HRL framework that formulates hierarchical policy learning as a bi-level optimization problem.<n>We show that DIPPER achieves up to 40% improvement over state-of-the-art baselines in sparse reward scenarios.
• Score: 75.9729413703531
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Hierarchical reinforcement learning (HRL) enables agents to solve complex, long-horizon tasks by decomposing them into manageable sub-tasks. However, HRL methods often suffer from two fundamental challenges: (i) non-stationarity, caused by the changing behavior of the lower-level policy during training, which destabilizes higher-level policy learning, and (ii) the generation of infeasible subgoals that lower-level policies cannot achieve. In this work, we introduce DIPPER, a novel HRL framework that formulates hierarchical policy learning as a bi-level optimization problem and leverages direct preference optimization (DPO) to train the higher-level policy using preference feedback. By optimizing the higher-level policy with DPO, we decouple higher-level learning from the non-stationary lower-level reward signal, thus mitigating non-stationarity. To further address the infeasible subgoal problem, DIPPER incorporates a regularization that tries to ensure the feasibility of subgoal tasks within the capabilities of the lower-level policy. Extensive experiments on challenging robotic navigation and manipulation benchmarks demonstrate that DIPPER achieves up to 40\% improvement over state-of-the-art baselines in sparse reward scenarios, highlighting its effectiveness in overcoming longstanding limitations of HRL.

Related papers

• Rethinking the Trust Region in LLM Reinforcement Learning [72.25890308541334]
  Proximal Policy Optimization (PPO) serves as the de facto standard algorithm for Large Language Models (LLMs)<n>We propose Divergence Proximal Policy Optimization (DPPO), which substitutes clipping with a more principled constraint.<n>DPPO achieves superior training and efficiency compared to existing methods, offering a more robust foundation for RL-based fine-tuning.
  arXiv  Detail & Related papers  (2026-02-04T18:59:04Z)
• A Step Back: Prefix Importance Ratio Stabilizes Policy Optimization [58.116300485427764]
  Reinforcement learning post-training can elicit reasoning behaviors in large language models.<n> token-level correction often leads to unstable training dynamics when the degree of off-policyness is large.<n>We propose a simple yet effective objective, Minimum Prefix Ratio (MinPRO)
  arXiv  Detail & Related papers  (2026-01-30T08:47:19Z)
• Polychromic Objectives for Reinforcement Learning [63.37185057794815]
  Reinforcement learning fine-tuning (RLFT) is a dominant paradigm for improving pretrained policies for downstream tasks.<n>We introduce an objective for policy methods that explicitly enforces the exploration and refinement of diverse generations.<n>We show how proximal policy optimization (PPO) can be adapted to optimize this objective.
  arXiv  Detail & Related papers  (2025-09-29T19:32:11Z)
• Reinforcement Learning with Anticipation: A Hierarchical Approach for Long-Horizon Tasks [3.79187263097166]
  Solving long-horizon goal-conditioned tasks remains a significant challenge in reinforcement learning.<n>We introduce Reinforcement Learning with Anticipation (RLA), a principled and potentially scalable framework designed to address these limitations.<n>Key feature of RLA is the training of the anticipation model, which is guided by a principle of value geometric consistency.
  arXiv  Detail & Related papers  (2025-09-06T00:10:15Z)
• On-Policy RL with Optimal Reward Baseline [109.47676554514193]
  On-Policy RL with Optimal reward baseline (OPO) is a novel and simplified reinforcement learning algorithm.<n>OPO emphasizes the importance of exact on-policy training, which empirically stabilizes the training process and enhances exploration.<n>Results demonstrate OPO's superior performance and training stability without additional models or regularization terms.
  arXiv  Detail & Related papers  (2025-05-29T15:58:04Z)
• Hierarchical Reinforcement Learning with Uncertainty-Guided Diffusional Subgoals [12.894271401094615]
  A key challenge in HRL is that the low-level policy changes over time, making it difficult for the high-level policy to generate effective subgoals.<n>We propose an approach that trains a conditional diffusion model regularized by a Gaussian Process (GP) prior to generate a complex variety of subgoals.<n>Building on this framework, we develop a strategy that selects subgoals from both the diffusion policy and GP's predictive mean.
  arXiv  Detail & Related papers  (2025-05-27T20:38:44Z)
• ULTHO: Ultra-Lightweight yet Efficient Hyperparameter Optimization in Deep Reinforcement Learning [50.53705050673944]
  We propose ULTHO, an ultra-lightweight yet powerful framework for fast HPO in deep RL within single runs. Specifically, we formulate the HPO process as a multi-armed bandit with clustered arms (MABC) and link it directly to long-term return optimization. We test ULTHO on benchmarks including ALE, Procgen, MiniGrid, and PyBullet.
  arXiv  Detail & Related papers  (2025-03-08T07:03:43Z)
• PEO: Improving Bi-Factorial Preference Alignment with Post-Training Policy Extrapolation [5.347428263669927]
  Post-Training Extrapolation Optimization (PEO) is a novel and efficient framework for bi-factorial alignment. PEO generates a family of optimal policies in a single training pass by leveraging a three-phase pipeline.
  arXiv  Detail & Related papers  (2025-03-03T06:56:39Z)
• HyperQ-Opt: Q-learning for Hyperparameter Optimization [0.0]
  This paper presents a novel perspective on HPO by formulating it as a sequential decision-making problem and leveraging Q-learning, a reinforcement learning technique. The approaches are evaluated for their ability to find optimal or near-optimal configurations within a limited number of trials. By shifting the paradigm toward policy-based optimization, this work contributes to advancing HPO methods for scalable and efficient machine learning applications.
  arXiv  Detail & Related papers  (2024-12-23T18:22:34Z)
• Entropy Controllable Direct Preference Optimization [3.536605202672355]
  We propose a simple modification to DPO, H-DPO, which allows for control over the entropy of the resulting policy. In our experiments, we show that H-DPO outperformed DPO across various tasks, demonstrating superior results in pass@$k$ evaluations for mathematical tasks.
  arXiv  Detail & Related papers  (2024-11-12T07:09:44Z)
• Joint Demonstration and Preference Learning Improves Policy Alignment with Human Feedback [58.049113055986375]
  We develop a single stage approach named Alignment with Integrated Human Feedback (AIHF) to train reward models and the policy. The proposed approach admits a suite of efficient algorithms, which can easily reduce to, and leverage, popular alignment algorithms. We demonstrate the efficiency of the proposed solutions with extensive experiments involving alignment problems in LLMs and robotic control problems in MuJoCo.
  arXiv  Detail & Related papers  (2024-06-11T01:20:53Z)
• LGR2: Language Guided Reward Relabeling for Accelerating Hierarchical Reinforcement Learning [23.878883576384002]
  Large language models (LLMs) have shown remarkable abilities in logical reasoning, in-context learning, and code generation.<n>We introduce LGR2, a novel HRL framework that leverages LLMs to generate language-guided reward functions for the higher-level policy.<n>To further enhance sample efficiency in sparse environments, we integrate goal-conditioned hindsight experience relabeling.
  arXiv  Detail & Related papers  (2024-06-09T18:40:24Z)
• Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF [82.7679132059169]
  Reinforcement learning from human feedback has emerged as a central tool for language model alignment. We propose a new algorithm for online exploration in RLHF, Exploratory Preference Optimization (XPO) XPO enjoys the strongest known provable guarantees and promising empirical performance.
  arXiv  Detail & Related papers  (2024-05-31T17:39:06Z)
• Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization [55.97310586039358]
  Diffusion models have garnered widespread attention in Reinforcement Learning (RL) for their powerful expressiveness and multimodality.<n>We propose a novel model-free diffusion-based online RL algorithm, Q-weighted Variational Policy Optimization (QVPO)<n>Specifically, we introduce the Q-weighted variational loss, which can be proved to be a tight lower bound of the policy objective in online RL under certain conditions.<n>We also develop an efficient behavior policy to enhance sample efficiency by reducing the variance of the diffusion policy during online interactions.
  arXiv  Detail & Related papers  (2024-05-25T10:45:46Z)
• Hyperparameter Optimization Can Even be Harmful in Off-Policy Learning and How to Deal with It [20.312864152544954]
  We show that naively applying an unbiased estimator of the generalization performance as a surrogate objective in HPO can cause an unexpected failure. We propose simple and computationally efficient corrections to the typical HPO procedure to deal with the aforementioned issues simultaneously.
  arXiv  Detail & Related papers  (2024-04-23T14:34:16Z)
• From $r$ to $Q^*$: Your Language Model is Secretly a Q-Function [50.812404038684505]
  We show that we can derive DPO in the token-level MDP as a general inverse Q-learning algorithm, which satisfies the Bellman equation. We discuss applications of our work, including information elicitation in multi-turn dialogue, reasoning, agentic applications and end-to-end training of multi-model systems.
  arXiv  Detail & Related papers  (2024-04-18T17:37:02Z)
• Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement [67.1393112206885]
  Large Language Models (LLMs) have shown promise as intelligent agents in interactive decision-making tasks. We introduce Entropy-Regularized Token-level Policy Optimization (ETPO), an entropy-augmented RL method tailored for optimizing LLMs at the token level. We assess the effectiveness of ETPO within a simulated environment that models data science code generation as a series of multi-step interactive tasks.
  arXiv  Detail & Related papers  (2024-02-09T07:45:26Z)
• Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints [26.274786600234876]
  The increasing capabilities of large language models (LLMs) raise opportunities for artificial general intelligence but amplify safety concerns. RLHF has emerged as a promising pathway towards AI alignment but brings forth challenges due to its complexity and dependence on a separate reward model. DPO has been proposed as an alternative, and it remains equivalent to RLHF under the reverse KL regularization constraint. We show that under certain $f$-divergences, including Jensen-Shannon divergence, forward KL divergences and $alpha$-divergences, the complex relationship between the reward and optimal policy can also be simplified
  arXiv  Detail & Related papers  (2023-09-28T08:29:44Z)
• PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback [106.63518036538163]
  We present a novel unified bilevel optimization-based framework, textsfPARL, formulated to address the recently highlighted critical issue of policy alignment in reinforcement learning. Our framework addressed these concerns by explicitly parameterizing the distribution of the upper alignment objective (reward design) by the lower optimal variable. Our empirical results substantiate that the proposed textsfPARL can address the alignment concerns in RL by showing significant improvements.
  arXiv  Detail & Related papers  (2023-08-03T18:03:44Z)
• Secrets of RLHF in Large Language Models Part I: PPO [81.01936993929127]
  Large language models (LLMs) have formulated a blueprint for the advancement of artificial general intelligence. reinforcement learning with human feedback (RLHF) emerges as the pivotal technological paradigm underpinning this pursuit. In this report, we dissect the framework of RLHF, re-evaluate the inner workings of PPO, and explore how the parts comprising PPO algorithms impact policy agent training.
  arXiv  Detail & Related papers  (2023-07-11T01:55:24Z)
• CRISP: Curriculum Inducing Primitive Informed Subgoal Prediction for Hierarchical Reinforcement Learning [25.84621883831624]
  CRISP is a curriculum-driven framework that tackles instability in hierarchical reinforcement learning.<n>It adaptively re-labels expert demonstrations to always generate reachable subgoals by the current low-level primitive.<n>It improves success rates by more than 40% over strong hierarchical and flat baselines.
  arXiv  Detail & Related papers  (2023-04-07T08:22:50Z)
• Adversarially Guided Subgoal Generation for Hierarchical Reinforcement Learning [5.514236598436977]
  We propose a novel HRL approach for mitigating the non-stationarity by adversarially enforcing the high-level policy to generate subgoals compatible with the current instantiation of the low-level policy. Experiments with state-of-the-art algorithms show that our approach significantly improves learning efficiency and overall performance of HRL in various challenging continuous control tasks.
  arXiv  Detail & Related papers  (2022-01-24T12:30:38Z)
• Improving Hyperparameter Optimization by Planning Ahead [3.8673630752805432]
  We propose a novel transfer learning approach, defined within the context of model-based reinforcement learning. We propose a new variant of model predictive control which employs a simple look-ahead strategy as a policy. Our experiments on three meta-datasets comparing to state-of-the-art HPO algorithms show that the proposed method can outperform all baselines.
  arXiv  Detail & Related papers  (2021-10-15T11:46:14Z)

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.