# Accelerating Goal-Directed Reinforcement Learning by Model Characterization

arXiv: https://arxiv.org/abs/1901.01977 · HTML: https://mlsanity.com/paper/1901.01977/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jan 2019.

## Built on by (most cited first, 1 of 1)

- [CostNet: An End-to-End Framework for Goal-Directed Reinforcement Learning](https://mlsanity.com/paper/2210.01805/) (2022)

## Abstract (arXiv)

We propose a hybrid approach aimed at improving the sample efficiency in goal-directed reinforcement learning. We do this via a two-step mechanism where firstly, we approximate a model from Model-Free reinforcement learning. Then, we leverage this approximate model along with a notion of reachability using Mean First Passage Times to perform Model-Based reinforcement learning. Built on such a novel observation, we design two new algorithms - Mean First Passage Time based Q-Learning (MFPT-Q) and Mean First Passage Time based DYNA (MFPT-DYNA), that have been fundamentally modified from the state-of-the-art reinforcement learning techniques. Preliminary results have shown that our hybrid approaches converge with much fewer iterations than their corresponding state-of-the-art counterparts and therefore requiring much fewer samples and much fewer training trials to converge.