Certified Anchor-Based Adaptation (CABA) is a post‑update gate for continual adaptation that reserves historical observations, compares old and candidate policies on frozen representations, and selects the largest interpolation coefficient whose worst‑anchor forward KL divergence stays within a declared budget. The method does not require action labels or complete trajectories and is supported by a theory‑led certification framework that provides uniform behavioral‑divergence bounds under representation‑coverage and Lipschitz assumptions. In a UCI Human Activity Recognition study, CABA reduced mean forgetting from 1.01 % to 0.00 % at a budget ε = 0.05, while slightly lowering final average accuracy.
arXiv:2610.20318v1 Announce Type: cross Abstract: Reinforcement-learning policies for robot locomotion can fail at deployment when operating conditions shift (e.g., rough or slippery terrain, payload...
The paper presents a convergence framework for deep $V$‑learning over a finite horizon $H$, deriving explicit bounds on policy loss by decomposing the Bellman update error into six residuals. It shows how $L^s$ concentrability controls expected $L^1$ loss, quantifies the impact of shared sampling across horizon levels, and provides optimal and near‑optimal sample allocations for statistical error rates. The work also establishes sharp action‑gap bounds under a margin condition, transfers optimal‑gap results to frozen‑iterate gaps, and offers consistency guarantees for generative‑reset approximate‑ERM procedures with exact action scores.
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 m...
arXiv:2609.14138v1 Announce Type: cross Abstract: As LLM agents become integrated into increasingly complex workflows, they must continually acquire new capabilities while retaining competence on pre...
arXiv:2608. 01130v1 Announce Type: new Abstract: A broad range of models face the mismatch where they are updated through trajectory losses but are evaluated by downstream task reward.
arXiv:2609.24380v1 Announce Type: new Abstract: RLVR has substantially improved the reasoning capabilities of LLMs. However, existing methods typically parameterize temporal progression in the Markov...
arXiv:2512. 23075v5 Announce Type: replace-cross Abstract: Policy gradient methods for Large Language Models optimize a policy $\pi_\theta$ via a surrogate objective computed from samples of a rollout policy $\pi_{\text{roll}}$.
arXiv:2607. 29172v1 Announce Type: cross Abstract: While robot foundation models are growing increasingly capable, the strongest models are typically trained on proprietary data and remain closed-source, limiting downstream users' ability to adapt them to new tasks, embodiments, and deployment settings.
arXiv:2610.02828v1 Announce Type: new Abstract: Adaptive LLM reinforcement-learning post-training changes multiple training actuators online, including rollout temperature, group size, clipping, KL r...
The paper introduces Keyframe Mnemonics, a self‑supervised approach that identifies critical observations (mnemonics) to aid behavior cloning in non‑Markovian settings. By training a policy conditioned on these keyframes, the method achieves perfect success rates on synthetic memory tasks and improves performance on a real‑robot manipulation benchmark, maintaining high success even at horizons far beyond training. The approach offers theoretical context‑retention guarantees and practical scalability to long‑horizon decision making.
The paper investigates how small action errors evolve when using action chunking in behavioural cloning. By injecting errors at each state and observing their growth under open‑loop (no replanning) and closed‑loop (replanning) regimes, the authors classify states as contracting, expanding, or unresolved. Across twelve manipulation tasks, they find that stable states are rare, error amplification is common, and that short‑horizon fitting can overestimate long‑horizon propagation. Predictors trained on camera and proprioceptive data can recover open‑loop stability but only partially capture closed‑loop dynamics, indicating that standard imitation learning does not reliably produce policies that contract errors when perturbed.
arXiv:2603.16157v2 Announce Type: replace-cross Abstract: While Reinforcement Learning (RL) enhances Large Language Model reasoning, on-policy algorithms like GRPO are sample-inefficient as they disc...