How Generalizable Is My Behavior Cloning Policy? A Statistical Approach to Trustworthy Performance Evaluation

• URL: http://arxiv.org/abs/2405.05439v2
• Date: Thu, 18 Jul 2024 18:45:25 GMT
• Title: How Generalizable Is My Behavior Cloning Policy? A Statistical Approach to Trustworthy Performance Evaluation
• Abstract summary: Behavior cloning policies are increasingly successful at solving complex tasks by learning from human demonstrations. We present a framework that provides a tight lower-bound on robot performance in an arbitrary environment. In experiments we evaluate policies for visuomotor manipulation in both simulation and hardware.
• Score: 17.638831964639834
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With the rise of stochastic generative models in robot policy learning, end-to-end visuomotor policies are increasingly successful at solving complex tasks by learning from human demonstrations. Nevertheless, since real-world evaluation costs afford users only a small number of policy rollouts, it remains a challenge to accurately gauge the performance of such policies. This is exacerbated by distribution shifts causing unpredictable changes in performance during deployment. To rigorously evaluate behavior cloning policies, we present a framework that provides a tight lower-bound on robot performance in an arbitrary environment, using a minimal number of experimental policy rollouts. Notably, by applying the standard stochastic ordering to robot performance distributions, we provide a worst-case bound on the entire distribution of performance (via bounds on the cumulative distribution function) for a given task. We build upon established statistical results to ensure that the bounds hold with a user-specified confidence level and tightness, and are constructed from as few policy rollouts as possible. In experiments we evaluate policies for visuomotor manipulation in both simulation and hardware. Specifically, we (i) empirically validate the guarantees of the bounds in simulated manipulation settings, (ii) find the degree to which a learned policy deployed on hardware generalizes to new real-world environments, and (iii) rigorously compare two policies tested in out-of-distribution settings. Our experimental data, code, and implementation of confidence bounds are open-source.

Related papers

• Active Real-World Factor-Based Evaluation for Generalist Robot Policies [13.386170952445868]
  Generalist robot manipulation policies have shown remarkable promise across a wide range of tasks.<n>We propose an active evaluation framework that treats policy evaluation as a sequential experimental design problem.<n>We conduct 2331 real-world evaluations across 3 tasks with 3 factor variations and find that our approach typically saves the evaluator at least 20-40% of trials.
  arXiv  Detail & Related papers  (2026-07-16T00:21:54Z)
• Stochastic MeanFlow Policies: One-Step Generative Control with Entropic Mirror Descent [53.828537014796574]
  Online off-policy reinforcement learning (RL) is shaped by two choices: the policy class and the update rule.<n>We propose MeanFlow Policies, a one-step generative policy class that maps noise to actions through a MeanFlow transformation.<n>Across seven MuJoCo benchmarks, S improves over Gaussian and generative baselines while retaining single-step inference efficiency.
  arXiv  Detail & Related papers  (2026-05-20T15:14:14Z)
• OGPO: Sample Efficient Full-Finetuning of Generative Control Policies [53.42266064673132]
  Generative control policies (GCPs) have emerged as effective parameterizations for robot learning.<n>This work introduces Off-policy Generative Policy Optimization (OGPO), a sample-efficient for finetuning GCPs.<n>OGPO achieves state-of-the-art performance on manipulation tasks spanning multi-task settings, high-precision insertion, and dexterous control.
  arXiv  Detail & Related papers  (2026-05-04T18:36:40Z)
• Off-Policy Evaluation for Ranking Policies under Deterministic Logging Policies [17.672063433232196]
  Off-Policy Evaluation (OPE) is an important practical problem in ranking systems.<n>The goal is to estimate the expected performance of a new ranking policy using only logged offline data collected under a different, logging policy.<n>We propose novel estimators, Click-based Inverse Propensity Score (CIPS), exploiting the intrinsicity of user click behavior to address this challenge.
  arXiv  Detail & Related papers  (2026-03-23T02:13:39Z)
• Robust Regularized Policy Iteration under Transition Uncertainty [6.7431287237221085]
  We formulate offline RL as robust policy optimization, treating the transition kernel as a decision variable within an uncertainty set.<n>We propose Robust Regularized Policy Iteration (RRPI), which replaces the intractable max-min bilevel objective with a tractable KL-regularized surrogate.<n>Experiments on D4RL benchmarks demonstrate that RRPI achieves strong average performance, outperforming recent baselines.
  arXiv  Detail & Related papers  (2026-03-10T08:18:27Z)
• Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows [11.159970460746164]
  Real-world fine-tuning of dexterous manipulation policies is challenging due to limited real-world interaction budgets and highly multimodal action distributions.<n>We present SOFT-FLOW, a sample-efficient off-policy fine-tuning framework with normalizing flow (NF)<n>This is the first demonstration of a likelihood-based, multimodal generative policy combined with chunk-level value learning on real robotic hardware.
  arXiv  Detail & Related papers  (2026-02-10T09:28:20Z)
• Reliable and Scalable Robot Policy Evaluation with Imperfect Simulators [9.868826622074899]
  SureSim is a framework to augment large-scale simulation with relatively small-scale real-world testing.<n>We leverage non-asymptotic mean estimation algorithms to provide confidence intervals on mean policy performance.<n>Our approach saves over (20-25%) of hardware evaluation effort to achieve similar bounds on policy performance.
  arXiv  Detail & Related papers  (2025-10-05T20:37:53Z)
• Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Composition [52.232968183793986]
  General Policy Composition (GPC) is a training-free method that enhances performance by combining the distributional scores of multiple pre-trained policies.<n>GPC consistently improves performance and adaptability across a diverse set of tasks.
  arXiv  Detail & Related papers  (2025-10-01T16:05:53Z)
• Evaluating Real-World Robot Manipulation Policies in Simulation [91.55267186958892]
  Control and visual disparities between real and simulated environments are key challenges for reliable simulated evaluation. We propose approaches for mitigating these gaps without needing to craft full-fidelity digital twins of real-world environments. We create SIMPLER, a collection of simulated environments for manipulation policy evaluation on common real robot setups.
  arXiv  Detail & Related papers  (2024-05-09T17:30:16Z)
• Learning Optimal Deterministic Policies with Stochastic Policy Gradients [62.81324245896716]
  Policy gradient (PG) methods are successful approaches to deal with continuous reinforcement learning (RL) problems. In common practice, convergence (hyper)policies are learned only to deploy their deterministic version. We show how to tune the exploration level used for learning to optimize the trade-off between the sample complexity and the performance of the deployed deterministic policy.
  arXiv  Detail & Related papers  (2024-05-03T16:45:15Z)
• Conformal Policy Learning for Sensorimotor Control Under Distribution Shifts [61.929388479847525]
  This paper focuses on the problem of detecting and reacting to changes in the distribution of a sensorimotor controller's observables. The key idea is the design of switching policies that can take conformal quantiles as input. We show how to design such policies by using conformal quantiles to switch between base policies with different characteristics.
  arXiv  Detail & Related papers  (2023-11-02T17:59:30Z)
• Off-Policy Evaluation for Large Action Spaces via Policy Convolution [60.6953713877886]
  Policy Convolution family of estimators uses latent structure within actions to strategically convolve the logging and target policies. Experiments on synthetic and benchmark datasets demonstrate remarkable mean squared error (MSE) improvements when using PC.
  arXiv  Detail & Related papers  (2023-10-24T01:00:01Z)
• Bi-Level Offline Policy Optimization with Limited Exploration [1.8130068086063336]
  We study offline reinforcement learning (RL) which seeks to learn a good policy based on a fixed, pre-collected dataset. We propose a bi-level structured policy optimization algorithm that models a hierarchical interaction between the policy (upper-level) and the value function (lower-level) We evaluate our model using a blend of synthetic, benchmark, and real-world datasets for offline RL, showing that it performs competitively with state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-10-10T02:45:50Z)
• PACER: A Fully Push-forward-based Distributional Reinforcement Learning Algorithm [28.48626438603237]
  PACER consists of a distributional critic, an actor and a sample-based encourager. Push-forward operator is leveraged in both the critic and actor to model the return distributions and policies respectively. A sample-based utility value policy gradient is established for the push-forward policy update.
  arXiv  Detail & Related papers  (2023-06-11T09:45:31Z)
• $K$-Nearest-Neighbor Resampling for Off-Policy Evaluation in Stochastic Control [0.6906005491572401]
  We propose a novel $K$-nearest neighbor reparametric procedure for estimating the performance of a policy from historical data. Our analysis allows for the sampling of entire episodes, as is common practice in most applications. Compared to other OPE methods, our algorithm does not require optimization, can be efficiently implemented via tree-based nearest neighbor search and parallelization, and does not explicitly assume a parametric model for the environment's dynamics.
  arXiv  Detail & Related papers  (2023-06-07T23:55:12Z)
• Conformal Off-Policy Evaluation in Markov Decision Processes [53.786439742572995]
  Reinforcement Learning aims at identifying and evaluating efficient control policies from data. Most methods for this learning task, referred to as Off-Policy Evaluation (OPE), do not come with accuracy and certainty guarantees. We present a novel OPE method based on Conformal Prediction that outputs an interval containing the true reward of the target policy with a prescribed level of certainty.
  arXiv  Detail & Related papers  (2023-04-05T16:45:11Z)
• Uncertainty Aware System Identification with Universal Policies [45.44896435487879]
  Sim2real transfer is concerned with transferring policies trained in simulation to potentially noisy real world environments. We propose Uncertainty-aware policy search (UncAPS), where we use Universal Policy Network (UPN) to store simulation-trained task-specific policies. We then employ robust Bayesian optimisation to craft robust policies for the given environment by combining relevant UPN policies in a DR like fashion.
  arXiv  Detail & Related papers  (2022-02-11T18:27:23Z)
• Constructing a Good Behavior Basis for Transfer using Generalized Policy Updates [63.58053355357644]
  We study the problem of learning a good set of policies, so that when combined together, they can solve a wide variety of unseen reinforcement learning tasks. We show theoretically that having access to a specific set of diverse policies, which we call a set of independent policies, can allow for instantaneously achieving high-level performance.
  arXiv  Detail & Related papers  (2021-12-30T12:20:46Z)

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.