# Path Planning using Reinforcement Learning: A Policy Iteration Approach

arXiv: https://arxiv.org/abs/2303.07535 · HTML: https://mlsanity.com/paper/2303.07535/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 49 references that are in the map.
- First posted on arXiv 13 Mar 2023.

## Builds on (most cited first, 12 of 12)

- [Practical Design Space Exploration](https://mlsanity.com/paper/1810.05236/) (2018)
- [Gated Path Planning Networks](https://mlsanity.com/paper/1806.06408/) (2018)
- [Minimax-optimal Inference from Partial Rankings](https://mlsanity.com/paper/1406.5638/) (2014)
- [Generalized Value Iteration Networks: Life Beyond Lattices](https://mlsanity.com/paper/1706.02416/) (2017)
- [MLGOPerf: An ML Guided Inliner to Optimize Performance](https://mlsanity.com/paper/2207.08389/) (2022)
- [Data-driven control of room temperature and bidirectional EV charging using deep reinforcement learning: simulations and experiments](https://mlsanity.com/paper/2103.01886/) (2021)
- [An Auto-tuning Framework for Autonomous Vehicles](https://mlsanity.com/paper/1808.04913/) (2018)
- [Reinforcement Learning Control of Robotic Knee with Human in the Loop by Flexible Policy Iteration](https://mlsanity.com/paper/2006.09008/) (2020)
- [SMASH: Sparse Matrix Atomic Scratchpad Hashing](https://mlsanity.com/paper/2105.14156/) (2021)
- [Generating GPU Compiler Heuristics using Reinforcement Learning](https://mlsanity.com/paper/2111.12055/) (2021)
- [Accelerating Polynomial Multiplication for Homomorphic Encryption on GPUs](https://mlsanity.com/paper/2209.01290/) (2022)
- [Learning Assisted Side Channel Delay Test for Detection of Recycled ICs](https://mlsanity.com/paper/2010.12704/) (2020)

## Abstract (arXiv)

With the impact of real-time processing being realized in the recent past, the need for efficient implementations of reinforcement learning algorithms has been on the rise. Albeit the numerous advantages of Bellman equations utilized in RL algorithms, they are not without the large search space of design parameters. This research aims to shed light on the design space exploration associated with reinforcement learning parameters, specifically that of Policy Iteration. Given the large computational expenses of fine-tuning the parameters of reinforcement learning algorithms, we propose an auto-tuner-based ordinal regression approach to accelerate the process of exploring these parameters and, in return, accelerate convergence towards an optimal policy. Our approach provides 1.82x peak speedup with an average of 1.48x speedup over the previous state-of-the-art.