paper
An Agency-Transferring Model-Free Policy Enhancement Technique
paperactiveprovisional
an-agency-transferring-model-free-policy-enhancement-technique-ff731883·1 events·first seen 8d agoAliases: An Agency-Transferring Model-Free Policy Enhancement Technique
More like this (12)
APPO: Agentic Procedural Policy OptimizationPreference Coordinated Multi-agent Policy OptimizationVector Policy OptimizationModel-Generated Agent Skills (paper)Learning Red Agent Policy from Observations for Neurosymbolic Autonomous Cyber AgentsEvolved Policy Gradientson-policy distillationPolicy Gradient MethodsProximal Policy OptimizationDenoising Diffusion Policy OptimizationMulti-Turn Evaluation of Deep Research Agents Under Process-Level FeedbackDifference-Aware Retrieval Policies for Imitation Learning
Recent events (1)
Agency-transferring technique improves RL policy training by bootstrapping from baseline policies
A new arXiv paper proposes a model-free reinforcement learning method that embeds an existing suboptimal baseline policy into training via an arbitration mechanism, progressively transferring control from the baseline to a trainable neural network. The approach yields high goal-reaching rates from the start of training and produces a standalone policy that outperforms the baseline without requiring it at inference time. Theoretical bounds on goal-reaching probability are derived, and empirical results on continuous-control benchmarks show competitive or superior returns compared to existing methods.