Efficient Test-Time Adaptation For Robot Policies

Motasem Alfarra; Pietro Mazzaglia; Markus Peschl; Daniel Dijkman; Christos Louizos

cs.ROOct 14, 2026

Efficient Test-Time Adaptation For Robot Policies

Authors: Motasem Alfarra, Pietro Mazzaglia, Markus Peschl, Daniel Dijkman, Christos Louizos

Organizations: Qualcomm AI Research, Amsterdam, the Netherlands

Abstract

Reinforcement-learning policies for robot locomotion can fail at deployment when operating conditions shift (e.g., rough or slippery terrain, payload changes, sensing degradation), and retraining or manual recalibration is often infeasible under on-device latency and memory constraints. We study test-time adaptation (TTA) for robotic control: adapting a pretrained policy online and in a self-supervised manner during execution, without access to rewards. Our starting point is a lightweight baseline that updates only the actor using a frozen pretrained critic as a deployment-time performance surrogate. Building on this, we introduce TEMPO, a test-time entropy-regularized, memory-guided policy optimization method that stabilizes critic-driven updates under severe shift. TEMPO combines (i) an entropy-promoting regularizer on the critic's predictive distribution to mitigate overconfident extrapolation, and (ii) a score-based memory, inspired by prioritized replay, that prioritizes low-value ("hard") observations and applies importance sampling to focus limited computation on the most informative deployment conditions. Across Go1, Go2, and G1 in MuJoCo Playground under four representative shifts and multiple architectures, TEMPO yields consistent gains, reaching up to 80% improvement in a single-device setting. We further validate on a physical Unitree Go2 with an added calf payload, where fully on-device adaptation improves performance over the non-adapted baseline across real-world episodes.

Figures & tables

Panel of Figure 1 — Figure 1: Motivation and pipeline. Left: Pretrained locomotion policies degrade as shift severity increases. Middle: Off-the-shelf TTA and prior RL adaptation baselines fail under a rocky-terrain shift. Right: TEMPO loop: execute $\pi_{\theta_{t}}$ , update memory $\mathcal{B}$ , and periodically adapt via Eq. ( 2 ).

Panel of Figure 2 — Figure 2: Main results on Go2 under deployment-time distribution shift. Top: episodic return. Bottom: average forward linear velocity. Shifts (left $\rightarrow$ right): $1-$ friction, calf mass, rough terrain, torso mass (severity increases along x-axis). As the severity of the domain shift increases, performance degrades more rapidly. Naive adaptation via QMAX recovers part of the performance drop. Our proposed TEMPO consistently provides the largest performance gain, especially under severe shifts.

	Mass on Calf = 2 kg				Mass on Torso = 5 kg
	Floor friction		Rocky terrain		Floor friction		Rocky terrain
Method	0.90	0.85	0.03	0.06	0.90	0.85	0.03	0.06
No Adapt	$9.2_{\pm 0.1}$	12.9 ±0.2	$19.9_{\pm 0.1}$	$14.5_{\pm 0.2}$	4.2 ±0.2	6.2 ±0.1	14.7 ±0.3	7.8 ±0.2
QMAX	$9.7_{\pm 0.2}$	13.4 ±0.4	$20.7_{\pm 0.1}$	$15.9_{\pm 0.2}$	4.8 ±0.1	7.0 ±0.3	17.3 ±0.5	9.9 ±0.2
TEMPO	10.4 ±0.2	14.4 ±0.1	21.2 ±0.3	17.5 ±0.2	5.6 ±0.2	9.0 ±0.4	20.1 ±0.2	14.6 ±0.2

Table 2: Performance Comparison Under Mixed Corruptions. We report the environment reward (six seeds) for the non-adapted policy, QMAX, and our proposed TEMPO when the policy is subjected to a composition of corruptions (e.g. mass on torso and rocky terrain simultaneously). Our proposed TEMPO consistently provides the best performance by a significant margin.

Panel of Figure 4 — Figure 4: Continual TTA under progressively increasing shift severity. We report environment rewards versus adaptation steps as the deployment shift intensifies over time. TEMPO recovers faster and converges to a higher performance plateau than QMAX across all corruptions.

Panel of Table 3 — Table 3: Ablating TEMPO . Average episodic return under increasing shift severity for three corruption families. Adding entropy regularization and score-based memory each improves over QMAX , and combining both ( TEMPO ) yields the best robustness across all severities.

Panel of Figure 5 — Figure 5: RMA ablation. Frozen RMA vs native RMA adaptation vs RMA+TEMPO. TEMPO provides consistent and significant additional gains.

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 8

Panel of Figure 6 — Figure 6: Generalization across architectures and embodiments. Rocky-terrain results (left $\rightarrow$ right): Fast-TD3 trained with domain randomization, SimBA-V2, and the G1 humanoid. TEMPO transfers without architecture-specific modifications and remains effective across settings.

	Go1				G1
Method	MC=4	MC=5	MT=7.5	MT=10	MT=2	MT=3	MT=5
No Adapt	18.9	16.3	13.6	6.8	21.3	17.5	10.0
QMAX	19.6	17.6	13.6	6.9	24.1	22.1	17.4
TEMPO	20.5	18.6	16.9	11.0	24.5	23.4	18.5

Appendix

Table 4: Additional results on Go1 and G1 under payload perturbations. MC denotes mass on calf and MT denotes mass on torso.

Panel of Figure 7 — Figure 7: Robustness to on-device adaptation hyperparameters. TEMPO is robust and performs best across different memory sizes (left), batch sizes (middle), and adaptation intervals (right). All experiments are run with Fast-TD3 on Go2 with Mass on Torso Corruption with severity of 7.5 kg.

Figure 9: Continual TTA followed by return to the source domain. Performance under a non-stationary deployment stream in which the severity of the domain shift increases over time and is then reset to nominal conditions. Left: mass-on-calf shift. Right: mass-on-torso shift. Architecture: Fast - TD3. Both QMAX and TEMPO recover source-domain performance immediately after the shift is removed, indicating no catastrophic forgetting despite prolonged adaptation under shift.

Panel of Figure 10 — Figure 10: Angular velocity tracking on Go2 under deployment-time distribution shift. We report angular velocity tracking error as a function of shift severity for four corruption families. Results are averaged over five seeds. Critic-guided test-time adaptation improves tracking accuracy relative to no adaptation, with TEMPO achieving the most stable and accurate angular velocity tracking, particularly under severe distribution shifts.

Explore similar work

AdaTempo: Learning Shared Relative Tempo from Demonstrations for Faster Robot Manipulation
Oct 2, 2026Jiale Cao, Yike Niu, Zhengrong Xue +1Robotic Manipulation Robot Imitation Learning
Fudan University · Tsinghua University
Scouting the Dynamics Gap: Test-Time Policy Adaptation via Action-Outcome Feedback
Sep 28, 2026Yishu Li, Liyuan Geng, Xinyi Mao +2Robot Policy Learning Test-Time Adaptation
Robotics Institute, Carnegie Mellon University · Computer Science and Technology, Tsinghua University
Proxy Policy Steering
Sep 8, 2026Chuanruo Ning, Tianrui Wang, Wei-Chiu Ma +1Robot Policy Adaptation Robot Foundation Models
Cornell University

Oct 2, 2026J/K move · Enter open · S save

AdaTempo: Learning Shared Relative Tempo from Demonstrations for Faster Robot Manipulation

Jiale Cao, Yike Niu, Zhengrong Xue, Huazhe Xu

Fudan University · Tsinghua University

Robotic Manipulation Robot Imitation Learning Visuomotor Policy Learning

Open paper AskPDF arXiv

Visuomotor policies trained via imitation learning often inherit the unnecessarily slow timing of teleoperated demonstrations. Yet uniform speedup is unreliable because different phases of a manipulation task tolerate acceleration differently. In this work, we introduce AdaTempo, a self-supervised method that accelerates visuomotor policies by exploiting shared relative-tempo structure in demonstrations. AdaTempo establishes phase correspondence, aggregates the aligned relative tempo into a consensus, and maps it to a continuous speedup profile used to resample demonstrations into accelerated training trajectories. Training standard policies such as ACT or Diffusion Policy on these resampled trajectories directly embeds the desired tempo in the learned behavior, without runtime tempo selection or online retiming. Extensive evaluations show that AdaTempo achieves up to a

3.57\times

speedup and yields a stronger success--speed trade-off than the original policies and representative acceleration baselines.

Abstract

Explore similar work

AdaTempo: Learning Shared Relative Tempo from Demonstrations for Faster Robot Manipulation

Scouting the Dynamics Gap: Test-Time Policy Adaptation via Action-Outcome Feedback

Proxy Policy Steering