Almanac
paper

An Agency-Transferring Model-Free Policy Enhancement Technique

paperactiveprovisionalan-agency-transferring-model-free-policy-enhancement-technique-ff731883·1 events·first seen 8d ago

Aliases: An Agency-Transferring Model-Free Policy Enhancement Technique

More like this (12)

Recent events (1)

4arXiv · cs.LG·8d ago·source ↗

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.