Succeed or Learn Slowly: Sample Efficient Off-Policy Reinforcement Learning for Mobile App Control

• URL: http://arxiv.org/abs/2509.01720v1
• Date: Mon, 01 Sep 2025 18:55:27 GMT
• Title: Succeed or Learn Slowly: Sample Efficient Off-Policy Reinforcement Learning for Mobile App Control
• Authors: Georgios Papoudakis, Thomas Coste, Jianye Hao, Jun Wang, Kun Shao,
• Abstract summary: This paper introduces Succeed or Learn Slowly (SoLS), a novel off-policyReinforcement learning algorithm evaluated on mobile app control tasks.<n>SoLS improves sample efficiency when fine-tuning foundation models for user interface navigation via a modified off-policy actor-critic approach.<n>We augment SoLS with Successful Transition Replay (STR), which prioritises learning from successful interactions.
• Score: 50.316067647636196
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement learning (RL) using foundation models for policy approximations in multi-turn tasks remains challenging. We identify two main limitations related to sparse reward settings and policy gradient updates, based on which we formulate a key insight: updates from positive samples with high returns typically do not require policy regularisation, whereas updates from negative samples, reflecting undesirable behaviour, can harm model performance. This paper introduces Succeed or Learn Slowly (SoLS), a novel off-policy RL algorithm evaluated on mobile app control tasks. SoLS improves sample efficiency when fine-tuning foundation models for user interface navigation via a modified off-policy actor-critic approach, applying direct policy updates for positive samples and conservative, regularised updates for negative ones to prevent model degradation. We augment SoLS with Successful Transition Replay (STR), which prioritises learning from successful interactions, further improving sample efficiency. We evaluate SoLS on the AndroidWorld benchmark, where it significantly outperforms existing methods (at least 17% relative increase), including prompt-engineering and RL approaches, while requiring substantially fewer computational resources than GPT-4o-based methods with 5-60x faster inference.

Related papers

• LLMs Can Learn to Reason Via Off-Policy RL [17.2941334301927]
  Reinforcement learning approaches for Large Language Models (LLMs) frequently use on-policy algorithms, such as PPO or GRPO.<n>We propose a novel off-policy RL algorithm that does not require these modifications: Optimal Advantage-based Policy Optimization with Lagged Inference policy (OAPL)<n>OAPL allows for efficient, effective post-training even with lags of more than 400 gradient steps between the training and inference policies, 100x more off-policy than prior approaches.
  arXiv  Detail & Related papers  (2026-02-22T22:12:51Z)
• BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping [69.74252624161652]
  We propose BAlanced Policy Optimization with Adaptive Clipping (BAPO)<n>BAPO dynamically adjusts clipping bounds to adaptively re-balance positive and negative contributions, preserve entropy, and stabilize RL optimization.<n>On AIME 2024 and AIME 2025 benchmarks, our 7B BAPO model surpasses open-source counterparts such as SkyWork-OR1-7B.
  arXiv  Detail & Related papers  (2025-10-21T12:55:04Z)
• Asymmetric Proximal Policy Optimization: mini-critics boost LLM reasoning [49.57517969069136]
  We introduce Asymmetric Proximal Policy Optimization (AsyPPO), a simple and scalable framework that restores the critics role while remaining efficient in large-model settings.<n>AsyPPO employs a set of lightweight mini-critics, each trained on disjoint prompt shards.<n>It consistently improves learning stability and performance across multiple benchmarks over strong baselines.
  arXiv  Detail & Related papers  (2025-10-02T04:24:27Z)
• Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents [24.972357127546772]
  Entropy-Modulated Policy Gradients (EMPG) is a framework that re-calibrates the learning signal based on step-wise uncertainty and the final task outcome.<n> EMPG amplifies updates for confident correct actions, penalizes confident errors, and attenuates updates from uncertain steps to stabilize exploration.
  arXiv  Detail & Related papers  (2025-09-11T08:50:01Z)
• Relative Entropy Pathwise Policy Optimization [56.86405621176669]
  We show how to construct a value-gradient driven, on-policy algorithm that allow training Q-value models purely from on-policy data.<n>We propose Relative Entropy Pathwise Policy Optimization (REPPO), an efficient on-policy algorithm that combines the sample-efficiency of pathwise policy gradients with the simplicity and minimal memory footprint of standard on-policy learning.
  arXiv  Detail & Related papers  (2025-07-15T06:24:07Z)
• LLM-Guided Reinforcement Learning: Addressing Training Bottlenecks through Policy Modulation [7.054214377609925]
  Reinforcement learning (RL) has achieved notable success in various domains.<n>Training effective policies for complex tasks remains challenging.<n>Existing approaches to mitigate training bottlenecks fall into two categories.
  arXiv  Detail & Related papers  (2025-05-27T03:40:02Z)
• VinePPO: Refining Credit Assignment in RL Training of LLMs [66.80143024475635]
  We propose VinePPO, a straightforward approach that leverages the flexibility of language environments to compute unbiased Monte Carlo-based estimates.<n>Our method consistently outperforms PPO and other baselines across MATH and GSM8K datasets in less wall-clock time.
  arXiv  Detail & Related papers  (2024-10-02T15:49:30Z)
• How Can LLM Guide RL? A Value-Based Approach [68.55316627400683]
  Reinforcement learning (RL) has become the de facto standard practice for sequential decision-making problems by improving future acting policies with feedback. Recent developments in large language models (LLMs) have showcased impressive capabilities in language understanding and generation, yet they fall short in exploration and self-improvement capabilities. We develop an algorithm named LINVIT that incorporates LLM guidance as a regularization factor in value-based RL, leading to significant reductions in the amount of data needed for learning.
  arXiv  Detail & Related papers  (2024-02-25T20:07:13Z)
• Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic [42.57662196581823]
  Learning high-quality $Q$-value functions plays a key role in the success of many modern off-policy deep reinforcement learning (RL) algorithms. Deviating from the common viewpoint, we observe that $Q$-values are often underestimated in the latter stage of the RL training process. We propose the Blended Exploitation and Exploration (BEE) operator, a simple yet effective approach that updates $Q$-value using both historical best-performing actions and the current policy.
  arXiv  Detail & Related papers  (2023-06-05T13:38:14Z)
• Jump-Start Reinforcement Learning [68.82380421479675]
  We present a meta algorithm that can use offline data, demonstrations, or a pre-existing policy to initialize an RL policy. In particular, we propose Jump-Start Reinforcement Learning (JSRL), an algorithm that employs two policies to solve tasks. We show via experiments that JSRL is able to significantly outperform existing imitation and reinforcement learning algorithms.
  arXiv  Detail & Related papers  (2022-04-05T17:25:22Z)
• Off-Policy Meta-Reinforcement Learning Based on Feature Embedding Spaces [14.029933823101084]
  We propose a novel off-policy meta-RL method, embedding learning and evaluation of uncertainty (ELUE) ELUE learns a belief model over the embedding space and a belief-conditional policy and Q-function. We demonstrate that ELUE outperforms state-of-the-art meta RL methods through experiments on meta-RL benchmarks.
  arXiv  Detail & Related papers  (2021-01-06T05:51:38Z)

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.