Neuro-Inspired Inverse Learning for Planning and Control

• URL: http://arxiv.org/abs/2605.24152v2
• Date: Tue, 26 May 2026 06:41:34 GMT
• Title: Neuro-Inspired Inverse Learning for Planning and Control
• Abstract summary: We present a neuro-inspired framework for embodied planning and control.<n>We build on three principles that enable fast and highly effective goal-directed behavior in the mammalian brain.<n>Our framework uses learned components, trained end-to-end through Inverse Learning.
• Score: 0.3437656066916039
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: We present a neuro-inspired framework for embodied planning and control. Building on three principles that enable fast and highly effective goal-directed behavior in the mammalian brain - paired forward/inverse internal models, open-loop multi-step motor commands, and sequential, hierarchical organization of action - our Inverter framework uses learned components, trained end-to-end through Inverse Learning (IL) and supplemented where natural by analytic or algorithmic modules; we formalize IL and delineate it from supervised, reinforcement, and imitation learning. IL bridges Reinforcement Learning (RL)-style amortization, which runs in a single forward pass but emits only one action at a time, and Optimal Control (OC)-style sequence planning over whole trajectories, but with iterative test-time computation. Single Inverters or hierarchical n=2 Inverter stacks match or improve on offline-RL and diffusion-planner baselines on all 3 maze2d and 6 antmaze D4RL variants by an average of +24.2% (range -1.9% to +78.2%), at one-to-two orders of magnitude less inference compute time. Distinctively, optimizing through the Forward Model (FoM) over the entire T-step action sequence - rather than per step - lets Inverters produce smooth, goal-coherent, trajectory-wide structure and reach control policies closer to the analytic optimum than the policy underlying the training data itself. We also identify a failure mode of IL: FoM hacking under narrow training-data coverage, which we mitigate by using random training data with broader coverage. As an application example, a Pulse Inverter synthesizes arbitrary single-qubit quantum gates with fidelity matching the standard iterative numerical baseline (GRAPE), at more than 1000x lower per-gate compute time. In summary, we conclude that IL enables a versatile class of world-interfaces, especially for latency- and resource-critical embodied AI.

Related papers

• Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think [43.01990826833761]
  Vision-Language-Action (VLA) models pre-trained on massive video-robot datasets have revolutionized robotic manipulation.<n>Despite being trained on diverse physical trajectories, they exhibit severe layer-wise representational redundancy.<n>We introduce a structural compression pipeline that is entirely training-free.<n>Downstream fine-tuning of this streamlined architecture yields a 40-50% reduction in training time and up to 30% faster real-time inference.
  arXiv  Detail & Related papers  (2026-06-18T13:57:12Z)
• EEVEE: Towards Test-time Prompt Learning in the Real World for Self-Improving Agents [64.96332056338923]
  EEVEE is the first multi-dataset test-time prompt learning framework for LLM agents.<n>It enables test-time prompt learning under real-world task streams.<n>EEVEE improves average multi-benchmark scores by 10.38 and 24.32 points over Qwen3-4B-Instruct and DeepSeek-V3.2.
  arXiv  Detail & Related papers  (2026-06-09T17:57:16Z)
• Intelligent Optimal Control of Rydberg Gates with Incremental-Update Deep Reinforcement Learning [10.771205594997445]
  We show a DRL-based framework for realizing Rydberg controlled-NOT gates with high speed and high fidelity.<n>By introducing an incremental-update learning policy, our framework effectively regularizes the exploration of the control landscape.<n>Our protocol achieves a peak average fidelity of 0.9991, significantly outperforming conventional methods and surpassing the critical fault-tolerant threshold.
  arXiv  Detail & Related papers  (2026-05-06T08:15:59Z)
• Dynamic Rank Reinforcement Learning for Adaptive Low-Rank Multi-Head Self Attention in Large Language Models [0.0]
  We propose Dynamic Rank Reinforcement Learning (DR-RL), a novel framework that adaptively optimize the low-rank factorization of Multi-Head Self-Attention (MHSA) in Large Language Models (LLMs)<n>DR-RL maintains downstream accuracy statistically equivalent to full-rank attention while significantly reducing Floating Point Operations (FLOPs)<n>This work bridges the gap between adaptive efficiency and theoretical rigor in MHSA, offering a principled, mathematically grounded alternative to rank reduction techniques in resource-constrained deep learning.
  arXiv  Detail & Related papers  (2025-12-17T21:09:19Z)
• Transformer-based Scalable Beamforming Optimization via Deep Residual Learning [12.79709425087431]
  unsupervised deep learning framework for downlink beamforming in large-scale MU-MISO channels.<n>Model is trained offline, allowing real-time inference through lightweight feedforward computations in dynamic communication environments.
  arXiv  Detail & Related papers  (2025-10-15T01:43:51Z)
• Learning to Reason as Action Abstractions with Scalable Mid-Training RL [55.24192942739207]
  An effective mid-training phase should identify a compact set of useful actions and enable fast selection.<n>We propose Reasoning as Action Abstractions (RA3), a scalable mid-training algorithm.
  arXiv  Detail & Related papers  (2025-09-30T05:34:20Z)
• How to Train Your LLM Web Agent: A Statistical Diagnosis [96.86317871461834]
  We present the first statistically grounded study on compute allocation for LLM web-agent post-training.<n>Our approach uses a two-stage pipeline, training a Llama 3.1 8B student to imitate a Llama 3.3 70B teacher via supervised fine-tuning (SFT) and on-policy reinforcement learning.<n>Our results show that combining SFT with on-policy RL consistently outperforms either approach alone on both WorkArena and MiniWob++.
  arXiv  Detail & Related papers  (2025-07-05T17:12:33Z)
• MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection [0.0]
  Matrix-Interpolated Dropout Layer (MID-L) dynamically selects and activates only the most informative neurons.<n>Experiments on six benchmarks, including MNIST, CIFAR-10, CIFAR-100, SVHN, UCI Adult, and IMDB, show that MID-L achieves up to average 55% reduction in active neurons.
  arXiv  Detail & Related papers  (2025-05-16T16:29:19Z)
• Action-Quantized Offline Reinforcement Learning for Robotic Skill Learning [68.16998247593209]
  offline reinforcement learning (RL) paradigm provides recipe to convert static behavior datasets into policies that can perform better than the policy that collected the data. In this paper, we propose an adaptive scheme for action quantization. We show that several state-of-the-art offline RL methods such as IQL, CQL, and BRAC improve in performance on benchmarks when combined with our proposed discretization scheme.
  arXiv  Detail & Related papers  (2023-10-18T06:07:10Z)
• Meta-Learning Adversarial Bandit Algorithms [55.72892209124227]
  We study online meta-learning with bandit feedback. We learn to tune online mirror descent generalization (OMD) with self-concordant barrier regularizers.
  arXiv  Detail & Related papers  (2023-07-05T13:52:10Z)
• Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Exploration [87.53543137162488]
  We propose an easy-to-implement online reinforcement learning (online RL) framework called textttMEX. textttMEX integrates estimation and planning components while balancing exploration exploitation automatically. It can outperform baselines by a stable margin in various MuJoCo environments with sparse rewards.
  arXiv  Detail & Related papers  (2023-05-29T17:25:26Z)
• Applications of Deep Learning to the Design of Enhanced Wireless Communication Systems [0.0]
  Deep learning (DL)-based systems are able to handle increasingly complex tasks for which no tractable models are available. This thesis aims at comparing different approaches to unlock the full potential of DL in the physical layer.
  arXiv  Detail & Related papers  (2022-05-02T21:02:14Z)

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.