Deliberate Practice: Learning Robot Skills under a Budget

• URL: http://arxiv.org/abs/2608.13415v1
• Date: Thu, 13 Aug 2026 16:09:25 GMT
• Title: Deliberate Practice: Learning Robot Skills under a Budget
• Abstract summary: We propose an active skill learning algorithm, emphDeliberate Practice (DP), that computes a provably emphbudget-optimal allocation.<n>DP estimates both the time needed to master skills and the cumulative reward of the task plans that the skills unlock.
• Score: 9.833236003698907
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We consider the problem of autonomously learning robot skills under a limited practice budget for sequential tasks. We propose an active skill learning algorithm, \emph{Deliberate Practice (DP)}, that computes a provably \emph{budget-optimal} allocation---practicing skills that maximize expected cumulative reward while being learnable within the budget. DP estimates both the time needed to master skills and the cumulative reward of the task plans that the skills unlock. Computing a budget-optimal allocation is challenging as it requires reasoning about combinatorially many skill plans over a large practice budget. Our key contribution is a bilinear program that can compute this exactly using off-the-shelf solvers. Through simulated and real-world experiments on long-horizon manipulation tasks, we show that our approach allows robots to optimally use limited practice time to acquire useful policies and improve long-horizon planning.

Related papers

• Better, Faster, Stronger: Programmatic Skill Learning Best Reduces Agent Cost [31.000338964323248]
  We argue that among all the different skill learning methods, those that view skills as programs can achieve the best cost reduction.<n>SpeedRunner is a coding agent that analyzes trajectories and skills for better performance on future tasks.
  arXiv  Detail & Related papers  (2026-08-11T18:42:23Z)
• Train Long, Think Short: Curriculum Learning for Efficient Reasoning [51.506559652495476]
  We propose a curriculum learning strategy for length-controlled reasoning.<n>Our method starts with generous token budgets and gradually tightens them over training.<n>Experiments on GSM8K, MATH500, SVAMP, College Math, and GSM+ demonstrate that curriculum-based training consistently outperforms fixed-budget baselines.
  arXiv  Detail & Related papers  (2025-08-12T13:48:03Z)
• SPIRE: Synergistic Planning, Imitation, and Reinforcement Learning for Long-Horizon Manipulation [58.14969377419633]
  We propose spire, a system that decomposes tasks into smaller learning subproblems and second combines imitation and reinforcement learning to maximize their strengths. We find that spire outperforms prior approaches that integrate imitation learning, reinforcement learning, and planning by 35% to 50% in average task performance.
  arXiv  Detail & Related papers  (2024-10-23T17:42:07Z)
• Practice Makes Perfect: Planning to Learn Skill Parameter Policies [34.51008914846429]
  In this work, we focus on the active learning problem of choosing which skills to practice to maximize expected future task success. We propose that the robot should estimate the competence of each skill, extrapolate the competence, and situate the skill in the task distribution through competence-aware planning. This approach is implemented within a fully autonomous system where the robot repeatedly plans, practices, and learns without any environment resets.
  arXiv  Detail & Related papers  (2024-02-22T23:58:26Z)
• Achieving mouse-level strategic evasion performance using real-time computational planning [59.60094442546867]
  Planning is an extraordinary ability in which the brain imagines and then enacts evaluated possible futures. We develop a more efficient biologically-inspired planning algorithm, TLPPO, based on work on how the ecology of an animal governs the value of spatial planning. We compare the performance of a real-time agent using TLPPO against the performance of live mice, all tasked with evading a robot predator.
  arXiv  Detail & Related papers  (2022-11-04T18:34:36Z)
• STAP: Sequencing Task-Agnostic Policies [22.25415946972336]
  We present Sequencing Task-Agnostic Policies (STAP) for training manipulation skills and coordinating their geometric dependencies at planning time to solve long-horizon tasks. Our experiments indicate that this objective function approximates ground truth plan feasibility. We demonstrate how STAP can be used for task and motion planning by estimating the geometric feasibility of skill sequences provided by a task planner.
  arXiv  Detail & Related papers  (2022-10-21T21:09:37Z)
• Skill-Based Reinforcement Learning with Intrinsic Reward Matching [77.34726150561087]
  We present Intrinsic Reward Matching (IRM), which unifies task-agnostic skill pretraining and task-aware finetuning. IRM enables us to utilize pretrained skills far more effectively than previous skill selection methods.
  arXiv  Detail & Related papers  (2022-10-14T00:04:49Z)
• Divide & Conquer Imitation Learning [75.31752559017978]
  Imitation Learning can be a powerful approach to bootstrap the learning process. We present a novel algorithm designed to imitate complex robotic tasks from the states of an expert trajectory. We show that our method imitates a non-holonomic navigation task and scales to a complex simulated robotic manipulation task with very high sample efficiency.
  arXiv  Detail & Related papers  (2022-04-15T09:56:50Z)
• Learning and Sequencing of Object-Centric Manipulation Skills for Industrial Tasks [16.308562047398542]
  We propose a rapid robot skill-sequencing algorithm, where the skills are encoded by object-centric hidden semi-Markov models. The learned skill models can encode multimodal (temporal and spatial) trajectory distributions. We demonstrate this approach on a 7 DoF robot arm for industrial assembly tasks.
  arXiv  Detail & Related papers  (2020-08-24T14:20:05Z)
• Emergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement Learning [81.12201426668894]
  We develop efficient reinforcement learning methods that acquire diverse skills without any reward function, and then repurpose these skills for downstream tasks. We show that our proposed algorithm provides substantial improvement in learning efficiency, making reward-free real-world training feasible. We also demonstrate that the learned skills can be composed using model predictive control for goal-oriented navigation, without any additional training.
  arXiv  Detail & Related papers  (2020-04-27T17:38:53Z)

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.