Tag
This paper introduces AdaPrefix-GRPO, a method that adaptively controls the length of correct solution prefixes provided to a model during GRPO training, maintaining a 50% success rate to maximize gradient signal. It significantly improves accuracy on hard math reasoning problems while reducing computational cost.
The paper proposes an active inference controller for adaptive traffic signal control in noisy IoT environments, outperforming DQN in idle times and CO2 emissions under sensor occlusion and adverse weather conditions.
Proposes CPSS, a runtime safety mechanism that converts cumulative cost constraints into adaptive state-level thresholds for safe reinforcement learning in nonstationary environments, demonstrating reduced violations in highway merging scenarios.
This paper introduces ACSAC, a reinforcement learning method that uses an adaptive chunk size actor-critic algorithm with a causal Transformer Q-network to handle long-horizon, sparse-reward tasks. It demonstrates state-of-the-art performance on manipulation tasks by dynamically adjusting action chunk sizes based on state-dependent needs.
This paper proposes a meta-control architecture using temporal self-attention for adaptive control of Euler-Lagrange systems with unobservable memory states. It demonstrates improved tracking performance over baseline methods on a 2-DOF manipulator while identifying failure modes in long-memory regimes.