Related papers: Action-Prior Denoising for Smooth Real-Time Chunki…

The remarkable progress in deep learning (DL) showcases outstanding results in various computer vision tasks. However, adaptation to real-time variations in data distributions remains an important challenge. Test-Time Training (TTT) was…

The ability to learn robust policies while generalizing over large discrete action spaces is an open challenge for intelligent systems, especially in noisy environments that face the curse of dimensionality. In this paper, we present a…

Reinforcement learning often produces high-frequency oscillatory control signals that undermine the safety and stability required for physical deployment. Explicit action chunking addresses this by predicting fixed-horizon trajectories but…

We study generalizable policy learning from demonstrations for complex low-level control (e.g., contact-rich object manipulations). We propose a novel hierarchical imitation learning method that utilizes sub-optimal demos. Firstly, we…

Autoregressive policies offer a compelling foundation for scalable robot learning by enabling discrete abstraction, token-level reasoning, and flexible inference. However, applying autoregressive modeling to continuous robot actions…

We study the broadcast transmission of a single file to an arbitrary number of receivers using Random Linear Network Coding (RLNC) in a network with unreliable channels. Due to the increased computational complexity of the decoding process…

Action chunking is a widely adopted approach in Learning from Demonstration (LfD). By modeling multi-step action chunks rather than single-step actions, action chunking significantly enhances modeling capabilities for human expert policies.…

Recurrent neural networks (RNNs) with deep test-time memorization modules, such as Titans and TTT, represent a promising, linearly-scaling paradigm distinct from Transformers. While these expressive models do not yet match the peak…

In an effort to overcome limitations of reward-driven feature learning in deep reinforcement learning (RL) from images, we propose decoupling representation learning from policy learning. To this end, we introduce a new unsupervised…

Action and observation delays commonly occur in many Reinforcement Learning applications, such as remote control scenarios. We study the anatomy of randomly delayed environments, and show that partially resampling trajectory fragments in…

Transformers are designed for discrete tokens, yet many real-world signals are continuous processes observed through noisy sampling. Discrete tokenizations (raw values, patches, finite differences) can be brittle in low signal-to-noise…

Reinforcement learning (RL) has demonstrated remarkable capability in acquiring robot skills, but learning each new skill still requires substantial data collection for training. The pretrain-and-finetune paradigm offers a promising…

Deep reinforcement learning can generate complex control policies, but requires large amounts of training data to work effectively. Recent work has attempted to address this issue by leveraging differentiable simulators. However, inherent…

The subject of this paper is reinforcement learning. Policies are considered here that produce actions based on states and random elements autocorrelated in subsequent time instants. Consequently, an agent learns from experiments that are…

Temporal credit assignment in reinforcement learning is challenging due to delayed and stochastic outcomes. Monte Carlo targets can bridge long delays between action and consequence but lead to high-variance targets due to stochasticity.…

Test-Time Compute (TTC) has emerged as a powerful paradigm for enhancing the performance of Large Language Models (LLMs) at inference, leveraging strategies such as Test-Time Training (TTT) and Retrieval-Augmented Generation (RAG). However,…

We present ATLAS-RTC, a runtime control system for autoregressive language models that enforces structured output during decoding. ATLAS-RTC monitors generation at each step, detects drift from output contracts using lightweight signals,…

In this pilot study, we propose a neuro-inspired approach that compresses temporal sequences into context-tagged chunks, where each tag represents a recurring structural unit or``community'' in the sequence. These tags are generated during…

The main objective of the paper is to improve the Round Robin (RR) algorithm using dynamic ITS by coalescing it with Shortest Remaining Time Next (SRTN) algorithm thus reducing the average waiting time, average turnaround time and the…

Temporal-difference (TD) methods learn state and action values efficiently by bootstrapping from their own future value predictions, but such a self-bootstrapping mechanism is prone to bootstrapping bias, where the errors in the value…