Towards Bridging the Gap between Large-Scale Pretraining and Efficient Finetuning for Humanoid Control

• URL: http://arxiv.org/abs/2601.21363v3
• Date: Sat, 21 Feb 2026 01:04:58 GMT
• Title: Towards Bridging the Gap between Large-Scale Pretraining and Efficient Finetuning for Humanoid Control
• Abstract summary: We find that off-policy Soft Actor-Critic (SAC) reliably supports large-scale pretraining of humanoid locomotion policies.<n>SAC-pretrained policies can be finetuned in new environments and out-of-distribution tasks using model-based methods.<n>Overall, the approach couples the wall-clock efficiency of large-scale simulation during pretraining with the sample efficiency of model-based learning during fine-tuning.
• Score: 18.618486126491334
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement learning (RL) is widely used for humanoid control, with on-policy methods such as Proximal Policy Optimization (PPO) enabling robust training via large-scale parallel simulation and, in some cases, zero-shot deployment to real robots. However, the low sample efficiency of on-policy algorithms limits safe adaptation to new environments. Although off-policy RL and model-based RL have shown improved sample efficiency, the gap between large-scale pretraining and efficient finetuning on humanoids still exists. In this paper, we find that off-policy Soft Actor-Critic (SAC), with large-batch update and a high Update-To-Data (UTD) ratio, reliably supports large-scale pretraining of humanoid locomotion policies, achieving zero-shot deployment on real robots. For adaptation, we demonstrate that these SAC-pretrained policies can be finetuned in new environments and out-of-distribution tasks using model-based methods. Data collection in the new environment executes a deterministic policy while stochastic exploration is instead confined to a physics-informed world model. This separation mitigates the risks of random exploration during adaptation while preserving exploratory coverage for improvement. Overall, the approach couples the wall-clock efficiency of large-scale simulation during pretraining with the sample efficiency of model-based learning during fine-tuning. For code and videos, see https://lift-humanoid.github.io

Related papers

• FlowDAgger: Human-in-the-Loop Adaptation of Generative Robot Policies in Latent Space [15.351960740594201]
  FlowDAgger is a sample- and compute-efficient method for adapting frozen generative robot policies from human interventions in latent space.<n>Our key idea is action inversion: each human expert action is mapped to the noise that would have produced it under the frozen base policy.<n>We evaluate FlowDAgger in simulation and on real-world bimanual and single-arm manipulation.
  arXiv  Detail & Related papers  (2026-07-09T19:07:33Z)
• TMRL: Diffusion Timestep-Modulated Pretraining Enables Exploration for Efficient Policy Finetuning [9.021212644908767]
  Fine-tuning pre-trained robot policies with reinforcement learning (RL) often inherits the bottlenecks introduced by pre-training with behavioral cloning (BC)<n>We present a unified framework that enables the exploration necessary to enable efficient robot policy finetuning.
  arXiv  Detail & Related papers  (2026-05-12T15:07:04Z)
• RFS: Reinforcement Learning with Residual Flow Steering for Dexterous Manipulation [7.500999283386335]
  Residual Flow Steering (RFS) is a data-efficient reinforcement learning framework for adapting pretrained generative policies.<n>RFS steers a pretrained flow-matching policy by jointly optimizing a residual action and a latent noise distribution.<n>We demonstrate the effectiveness of RFS on dexterous manipulation tasks, showing efficient fine-tuning in both simulation and real-world settings.
  arXiv  Detail & Related papers  (2026-02-02T08:11:57Z)
• 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)
• SPACeR: Self-Play Anchoring with Centralized Reference Models [50.55045557371374]
  Sim agent policies are realistic, human-like, fast, and scalable in multi-agent settings.<n>Recent progress in imitation learning with large diffusion-based or tokenized models has shown that behaviors can be captured directly from human driving data.<n>We propose SPACeR, a framework that leverages a pretrained tokenized autoregressive motion model as a central reference policy.
  arXiv  Detail & Related papers  (2025-10-20T19:53:02Z)
• Succeed or Learn Slowly: Sample Efficient Off-Policy Reinforcement Learning for Mobile App Control [50.316067647636196]
  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.
  arXiv  Detail & Related papers  (2025-09-01T18:55:27Z)
• Optimal Transport-Guided Source-Free Adaptation for Face Anti-Spoofing [58.56017169759816]
  We introduce a novel method in which the face anti-spoofing model can be adapted by the client itself to a target domain at test time.<n>Specifically, we develop a prototype-based base model and an optimal transport-guided adaptor.<n>In cross-domain and cross-attack settings, compared with recent methods, our method achieves average relative improvements of 19.17% in HTER and 8.58% in AUC.
  arXiv  Detail & Related papers  (2025-03-29T06:10:34Z)
• Autonomous Vehicle Controllers From End-to-End Differentiable Simulation [57.278726604424556]
  We propose a differentiable simulator and design an analytic policy gradients (APG) approach to training AV controllers.<n>Our proposed framework brings the differentiable simulator into an end-to-end training loop, where gradients of environment dynamics serve as a useful prior to help the agent learn a more grounded policy.<n>We find significant improvements in performance and robustness to noise in the dynamics, as well as overall more intuitive human-like handling.
  arXiv  Detail & Related papers  (2024-09-12T11:50:06Z)
• Model-based Safe Deep Reinforcement Learning via a Constrained Proximal Policy Optimization Algorithm [4.128216503196621]
  We propose an On-policy Model-based Safe Deep RL algorithm in which we learn the transition dynamics of the environment in an online manner. We show that our algorithm is more sample efficient and results in lower cumulative hazard violations as compared to constrained model-free approaches.
  arXiv  Detail & Related papers  (2022-10-14T06:53:02Z)
• Off Environment Evaluation Using Convex Risk Minimization [0.0]
  We propose a convex risk minimization algorithm to estimate the model mismatch between the simulator and the target domain. We show that this estimator can be used along with the simulator to evaluate performance of an RL agents in the target domain.
  arXiv  Detail & Related papers  (2021-12-21T21:31:54Z)
• MUSBO: Model-based Uncertainty Regularized and Sample Efficient Batch Optimization for Deployment Constrained Reinforcement Learning [108.79676336281211]
  Continuous deployment of new policies for data collection and online learning is either cost ineffective or impractical. We propose a new algorithmic learning framework called Model-based Uncertainty regularized and Sample Efficient Batch Optimization. Our framework discovers novel and high quality samples for each deployment to enable efficient data collection.
  arXiv  Detail & Related papers  (2021-02-23T01:30:55Z)

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.