arXiv Machine Learning September 29, 2026 By Chainesh Gautam, Raghuram Bharadwaj Diddigi, Chandramouli Kamanchi, Pankaj Dayama, Sumanta Mukherjee, Kameshwaran Sampath

Trust Guided Decision Transformer

Read the original on arXiv Machine Learning →

The paper introduces Trust Guided Decision Transformer (TGDT), a method that mitigates performance degradation in Decision Transformers during long rollouts by monitoring the model’s next‑state prediction error. TGDT evaluates multiple recent context suffixes, filters out those whose prediction error exceeds a calibrated threshold, and then selects the highest‑value action from the remaining trusted suffixes using a frozen critic. Experiments on D4RL navigation and locomotion tasks demonstrate that TGDT reduces persistent high‑error runs and improves returns compared to vanilla Decision Transformer and other context‑control baselines.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Sep 22

Statistical Convergence of Transformer Encoder-Accelerated Robust Reinforcement Learning

arXiv:2609.23775v1 Announce Type: new Abstract: Obtaining the optimal action-value function in Markov decision processes is computationally intensive in large state--action spaces. In this study, we...

By Suman Banerjee, Hiroyasu Tsukamoto

llms reinforcement-learning

arXiv Machine Learning

Sep 21

Adaptive Rollout Truncation Based on Epistemic Uncertainty for Efficient Offline World Model Training

The paper introduces an adaptive rollout truncation method for offline world model training that uses epistemic uncertainty to decide when to stop autoregressive rollouts. By calibrating a threshold during a warm‑up phase, the approach replaces fixed‑horizon rollouts with uncertainty‑driven truncation, evaluated with ensemble and Monte Carlo dropout estimators. Experiments on ANYmal‑D and ANT demonstrate that this strategy matches or surpasses fixed‑horizon training while reducing cumulative rollout steps by about 72%.

By Nikodem Sebastian Zymla, Laurin Thiele, Johannes Pitz

robotics

arXiv AI

Aug 5

ValueFormer: A Causal Transformer Value Function with Stage-Aware Labels for Semi-Autonomous Vision-Language-Action Policies

arXiv:2608. 02958v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) policies trained by behavior cloning fail silently: from the action stream alone, a collapsing rollout looks much like one making clean progress, because imitation supplies no notion of progress.

By Inkyu Sa, Konstantin Stulov, Rajat Bhageria

llms agents reinforcement-learning robotics multimodal

arXiv Machine Learning

Sep 1

World Model Control by Trajectory Reachability Metrics

arXiv:2605.22164v2 Announce Type: replace Abstract: Latent world models can learn representations that contain information needed for control, while the downstream controller may still rank candidate...

By Liangyu Li, Shengzhi Wang, Libin Qiu, Mingliang Xiong, Qingwen Liu

arXiv Machine Learning

Jul 31

Exact Action Values Are Not Enough: Rollout-Verified Reinforcement Fine-Tuning of a Reasoning Model for Multi-Zone VAV Control

arXiv:2607. 27914v1 Announce Type: new Abstract: Multi-zone variable-air-volume control must balance thermal comfort, indoor air quality, and electricity use across several continuous actuators.

By Takumi Shioda, Kohei Terashima, Tatsuo Nagai

llms reinforcement-learning fine-tuning

arXiv Machine Learning

Jun 8

Chunking the Critic: A Transformer-based Soft Actor-Critic with N-Step Returns

arXiv:2503. 03660v4 Announce Type: replace Abstract: We introduce a sequence-conditioned critic for Soft Actor-Critic (SAC) that models trajectory context with a lightweight Transformer and trains on aggregated $N$-step targets.

By Dong Tian, Onur Celik, Gerhard Neumann

llms rag reinforcement-learning benchmarks

One email a morning, machine-written

Related stories

Statistical Convergence of Transformer Encoder-Accelerated Robust Reinforcement Learning

Adaptive Rollout Truncation Based on Epistemic Uncertainty for Efficient Offline World Model Training

ValueFormer: A Causal Transformer Value Function with Stage-Aware Labels for Semi-Autonomous Vision-Language-Action Policies

World Model Control by Trajectory Reachability Metrics

Exact Action Values Are Not Enough: Rollout-Verified Reinforcement Fine-Tuning of a Reasoning Model for Multi-Zone VAV Control

Chunking the Critic: A Transformer-based Soft Actor-Critic with N-Step Returns