LGR2: Language Guided Reward Relabeling for Accelerating Hierarchical Reinforcement Learning

• URL: http://arxiv.org/abs/2406.05881v6
• Date: Wed, 27 Aug 2025 17:57:18 GMT
• Title: LGR2: Language Guided Reward Relabeling for Accelerating Hierarchical Reinforcement Learning
• Authors: Utsav Singh, Pramit Bhattacharyya, Vinay P. Namboodiri,
• Abstract summary: 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.
• Score: 23.878883576384002
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Large language models (LLMs) have shown remarkable abilities in logical reasoning, in-context learning, and code generation. However, translating natural language instructions into effective robotic control policies remains a significant challenge, especially for tasks requiring long-horizon planning and operating under sparse reward conditions. Hierarchical Reinforcement Learning (HRL) provides a natural framework to address this challenge in robotics; however, it typically suffers from non-stationarity caused by the changing behavior of the lower-level policy during training, destabilizing higher-level policy learning. We introduce LGR2, a novel HRL framework that leverages LLMs to generate language-guided reward functions for the higher-level policy. By decoupling high-level reward generation from low-level policy changes, LGR2 fundamentally mitigates the non-stationarity problem in off-policy HRL, enabling stable and efficient learning. To further enhance sample efficiency in sparse environments, we integrate goal-conditioned hindsight experience relabeling. Extensive experiments across simulated and real-world robotic navigation and manipulation tasks demonstrate LGR2 outperforms both hierarchical and non-hierarchical baselines, achieving over 55% success rates on challenging tasks and robust transfer to real robots, without additional fine-tuning.

Related papers

• EVOLVE-VLA: Test-Time Training from Environment Feedback for Vision-Language-Action Models [57.75717492488268]
  Vision-Language-Action (VLA) models have advanced robotic manipulation by leveraging large language models.<n>Supervised Finetuning (SFT) requires hundreds of demonstrations per task, rigidly memorizing trajectories, and failing to adapt when deployment conditions deviate from training.<n>We introduce EVOLVE-VLA, a test-time training framework enabling VLAs to continuously adapt through environment interaction with minimal or zero task-specific demonstrations.
  arXiv  Detail & Related papers  (2025-12-16T18:26:38Z)
• Human-in-the-loop Online Rejection Sampling for Robotic Manipulation [55.99788088622936]
  Hi-ORS stabilizes value estimation by filtering out negatively rewarded samples during online fine-tuning.<n>Hi-ORS fine-tunes a pi-base policy to master contact-rich manipulation in just 1.5 hours of real-world training.
  arXiv  Detail & Related papers  (2025-10-30T11:53:08Z)
• Learning Affordances at Inference-Time for Vision-Language-Action Models [50.93181349331096]
  In robotics, Vision-Language-Action models (VLAs) offer a promising path towards solving complex control tasks.<n>We introduce Learning from Inference-Time Execution (LITEN), which connects a VLA low-level policy to a high-level VLM that conditions on past experiences.<n>Our approach iterates between a reasoning phase that generates and executes plans for the low-level VLA, and an assessment phase that reflects on the resulting execution.
  arXiv  Detail & Related papers  (2025-10-22T16:43:29Z)
• RLVMR: Reinforcement Learning with Verifiable Meta-Reasoning Rewards for Robust Long-Horizon Agents [43.806220882212386]
  RLVMR integrates dense, process-level supervision into end-to-end RL by rewarding verifiable, meta-reasoning behaviors.<n>On the challenging ALFWorld and ScienceWorld benchmarks, RLVMR achieves new state-of-the-art results.
  arXiv  Detail & Related papers  (2025-07-30T17:00:48Z)
• COMBO-Grasp: Learning Constraint-Based Manipulation for Bimanual Occluded Grasping [56.907940167333656]
  Occluded robot grasping is where the desired grasp poses are kinematically infeasible due to environmental constraints such as surface collisions.<n>Traditional robot manipulation approaches struggle with the complexity of non-prehensile or bimanual strategies commonly used by humans.<n>We introduce Constraint-based Manipulation for Bimanual Occluded Grasping (COMBO-Grasp), a learning-based approach which leverages two coordinated policies.
  arXiv  Detail & Related papers  (2025-02-12T01:31:01Z)
• Exploiting Hybrid Policy in Reinforcement Learning for Interpretable Temporal Logic Manipulation [12.243491328213217]
  Reinforcement Learning (RL) based methods have been increasingly explored for robot learning. We propose a Temporal-Logic-guided Hybrid policy framework (HyTL) which leverages three-level decision layers to improve the agent's performance. We evaluate HyTL on four challenging manipulation tasks, which demonstrate its effectiveness and interpretability.
  arXiv  Detail & Related papers  (2024-12-29T03:34:53Z)
• Hierarchical Preference Optimization: Learning to achieve goals via feasible subgoals prediction [71.81851971324187]
  This work introduces Hierarchical Preference Optimization (HPO), a novel approach to hierarchical reinforcement learning (HRL) HPO addresses non-stationarity and infeasible subgoal generation issues when solving complex robotic control tasks. Experiments on challenging robotic navigation and manipulation tasks demonstrate impressive performance of HPO, where it shows an improvement of up to 35% over the baselines.
  arXiv  Detail & Related papers  (2024-11-01T04:58:40Z)
• Retrieval-Augmented Hierarchical in-Context Reinforcement Learning and Hindsight Modular Reflections for Task Planning with LLMs [8.55917897789612]
  We propose Retrieval-Augmented in-context reinforcement Learning (RAHL) for large language models. RAHL decomposes complex tasks into sub-tasks using an LLM-based high-level policy. We show that RAHL can achieve an improvement in performance in 9%, 42%, and 10% in 5 episodes of execution in strong baselines.
  arXiv  Detail & Related papers  (2024-08-12T22:40:01Z)
• Beyond Human Preferences: Exploring Reinforcement Learning Trajectory Evaluation and Improvement through LLMs [12.572869123617783]
  Reinforcement learning (RL) faces challenges in evaluating policy trajectories within intricate game tasks. PbRL presents a pioneering framework that capitalizes on human preferences as pivotal reward signals. We propose a LLM-enabled automatic preference generation framework named LLM4PG.
  arXiv  Detail & Related papers  (2024-06-28T04:21:24Z)
• Aquatic Navigation: A Challenging Benchmark for Deep Reinforcement Learning [53.3760591018817]
  We propose a new benchmarking environment for aquatic navigation using recent advances in the integration between game engines and Deep Reinforcement Learning. Specifically, we focus on PPO, one of the most widely accepted algorithms, and we propose advanced training techniques. Our empirical evaluation shows that a well-designed combination of these ingredients can achieve promising results.
  arXiv  Detail & Related papers  (2024-05-30T23:20:23Z)
• InCoRo: In-Context Learning for Robotics Control with Feedback Loops [4.702566749969133]
  InCoRo is a system that uses a classical robotic feedback loop composed of an LLM controller, a scene understanding unit, and a robot. We highlight the generalization capabilities of our system and show that InCoRo surpasses the prior art in terms of the success rate. This research paves the way towards building reliable, efficient, intelligent autonomous systems that adapt to dynamic environments.
  arXiv  Detail & Related papers  (2024-02-07T19:01:11Z)
• Logical Specifications-guided Dynamic Task Sampling for Reinforcement Learning Agents [9.529492371336286]
  Reinforcement Learning (RL) has made significant strides in enabling artificial agents to learn diverse behaviors. We propose a novel approach, called Logical Specifications-guided Dynamic Task Sampling (LSTS) LSTS learns a set of RL policies to guide an agent from an initial state to a goal state based on a high-level task specification.
  arXiv  Detail & Related papers  (2024-02-06T04:00:21Z)
• SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning [85.21378553454672]
  We develop a library containing a sample efficient off-policy deep RL method, together with methods for computing rewards and resetting the environment. We find that our implementation can achieve very efficient learning, acquiring policies for PCB board assembly, cable routing, and object relocation. These policies achieve perfect or near-perfect success rates, extreme robustness even under perturbations, and exhibit emergent robustness recovery and correction behaviors.
  arXiv  Detail & Related papers  (2024-01-29T10:01:10Z)
• Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Data [101.43350024175157]
  Self-supervised learning has the potential to decrease the amount of human annotation and engineering effort required to learn control strategies. Our work builds on prior work showing that the reinforcement learning (RL) itself can be cast as a self-supervised problem. We demonstrate that a self-supervised RL algorithm based on contrastive learning can solve real-world, image-based robotic manipulation tasks.
  arXiv  Detail & Related papers  (2023-06-06T01:36:56Z)
• CRISP: Curriculum Inducing Primitive Informed Subgoal Prediction for Hierarchical Reinforcement Learning [25.84621883831624]
  We present CRISP, a novel HRL algorithm that generates a curriculum of achievable subgoals for evolving lower-level primitives. CRISP uses the lower level primitive to periodically perform data relabeling on a handful of expert demonstrations. We demonstrate that CRISP demonstrates impressive generalization in real world scenarios.
  arXiv  Detail & Related papers  (2023-04-07T08:22:50Z)
• Efficient Learning of High Level Plans from Play [57.29562823883257]
  We present Efficient Learning of High-Level Plans from Play (ELF-P), a framework for robotic learning that bridges motion planning and deep RL. We demonstrate that ELF-P has significantly better sample efficiency than relevant baselines over multiple realistic manipulation tasks.
  arXiv  Detail & Related papers  (2023-03-16T20:09:47Z)
• Leveraging Sequentiality in Reinforcement Learning from a Single Demonstration [68.94506047556412]
  We propose to leverage a sequential bias to learn control policies for complex robotic tasks using a single demonstration. We show that DCIL-II can solve with unprecedented sample efficiency some challenging simulated tasks such as humanoid locomotion and stand-up.
  arXiv  Detail & Related papers  (2022-11-09T10:28:40Z)
• Weakly Supervised Disentangled Representation for Goal-conditioned Reinforcement Learning [15.698612710580447]
  We propose a skill learning framework DR-GRL that aims to improve the sample efficiency and policy generalization. In a weakly supervised manner, we propose a Spatial Transform AutoEncoder (STAE) to learn an interpretable and controllable representation. We empirically demonstrate that DR-GRL significantly outperforms the previous methods in sample efficiency and policy generalization.
  arXiv  Detail & Related papers  (2022-02-28T09:05:14Z)
• 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)
• Hierarchical Reinforcement Learning with Timed Subgoals [11.758625350317274]
  We introduce Hierarchical reinforcement learning with Timed Subgoals (HiTS) HiTS enables the agent to adapt its timing to a dynamic environment by specifying what goal state is to be reached and also when. Experiments show that our method is capable of sample-efficient learning where an existing state-of-the-art subgoal-based HRL method fails to learn stable solutions.
  arXiv  Detail & Related papers  (2021-12-06T15:11:19Z)
• Accelerating Robotic Reinforcement Learning via Parameterized Action Primitives [92.0321404272942]
  Reinforcement learning can be used to build general-purpose robotic systems. However, training RL agents to solve robotics tasks still remains challenging. In this work, we manually specify a library of robot action primitives (RAPS), parameterized with arguments that are learned by an RL policy. We find that our simple change to the action interface substantially improves both the learning efficiency and task performance.
  arXiv  Detail & Related papers  (2021-10-28T17:59:30Z)
• Safe-Critical Modular Deep Reinforcement Learning with Temporal Logic through Gaussian Processes and Control Barrier Functions [3.5897534810405403]
  Reinforcement learning (RL) is a promising approach and has limited success towards real-world applications. In this paper, we propose a learning-based control framework consisting of several aspects. We show such an ECBF-based modular deep RL algorithm achieves near-perfect success rates and guard safety with a high probability.
  arXiv  Detail & Related papers  (2021-09-07T00:51:12Z)
• Persistent Reinforcement Learning via Subgoal Curricula [114.83989499740193]
  Value-accelerated Persistent Reinforcement Learning (VaPRL) generates a curriculum of initial states. VaPRL reduces the interventions required by three orders of magnitude compared to episodic reinforcement learning.
  arXiv  Detail & Related papers  (2021-07-27T16:39:45Z)
• ReLMoGen: Leveraging Motion Generation in Reinforcement Learning for Mobile Manipulation [99.2543521972137]
  ReLMoGen is a framework that combines a learned policy to predict subgoals and a motion generator to plan and execute the motion needed to reach these subgoals. Our method is benchmarked on a diverse set of seven robotics tasks in photo-realistic simulation environments. ReLMoGen shows outstanding transferability between different motion generators at test time, indicating a great potential to transfer to real robots.
  arXiv  Detail & Related papers  (2020-08-18T08:05:15Z)

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.