# Exploring Parity Challenges in Reinforcement Learning through Curriculum Learning with Noisy Labels

arXiv: https://arxiv.org/abs/2312.05379 · HTML: https://mlsanity.com/paper/2312.05379/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 31 references that are in the map.
- First posted on arXiv 8 Dec 2023.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning from Noisy Labels with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2007.08199/) (2020)
- [Theoretical Limitations of Self-Attention in Neural Sequence Models](https://mlsanity.com/paper/1906.06755/) (2019)
- [PonderNet: Learning to Ponder](https://mlsanity.com/paper/2107.05407/) (2021)
- [Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates](https://mlsanity.com/paper/1910.03231/) (2019)
- [Failures of Gradient-Based Deep Learning](https://mlsanity.com/paper/1703.07950/) (2017)
- [Reinforcement Learning with Perturbed Rewards](https://mlsanity.com/paper/1810.01032/) (2018)
- [Learning Parities with Neural Networks](https://mlsanity.com/paper/2002.07400/) (2020)
- [Reinforcement Learning with a Corrupted Reward Channel](https://mlsanity.com/paper/1705.08417/) (2017)
- [Classification with Asymmetric Label Noise: Consistency and Maximal Denoising](https://mlsanity.com/paper/1303.1208/) (2013)
- [Do RNN and LSTM have Long Memory?](https://mlsanity.com/paper/2006.03860/) (2020)
- [Fast Learning Requires Good Memory: A Time-Space Lower Bound for Parity Learning](https://mlsanity.com/paper/1602.05161/) (2016)
- [Provable Advantage of Curriculum Learning on Parity Targets with Mixed Inputs](https://mlsanity.com/paper/2306.16921/) (2023)
- [A Mathematical Model for Curriculum Learning for Parities](https://mlsanity.com/paper/2301.13833/) (2023)
- [Regularizing Towards Permutation Invariance in Recurrent Models](https://mlsanity.com/paper/2010.13055/) (2020)
- [Impartial Games: A Challenge for Reinforcement Learning](https://mlsanity.com/paper/2205.12787/) (2022)

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

- [Overcoming a Learning Bottleneck in Impartial Games: A Circuit Complexity Approach](https://mlsanity.com/paper/2411.06403/) (2024)

## Abstract (arXiv)

This paper delves into applying reinforcement learning (RL) in strategy games, particularly those characterized by parity challenges, as seen in specific positions of Go and Chess and a broader range of impartial games. We propose a simulated learning process, structured within a curriculum learning framework and augmented with noisy labels, to mirror the intricacies of self-play learning scenarios. This approach thoroughly analyses how neural networks (NNs) adapt and evolve from elementary to increasingly complex game positions. Our empirical research indicates that even minimal label noise can significantly impede NNs' ability to discern effective strategies, a difficulty that intensifies with the growing complexity of the game positions. These findings underscore the urgent need for advanced methodologies in RL training, specifically tailored to counter the obstacles imposed by noisy evaluations. The development of such methodologies is crucial not only for enhancing NN proficiency in strategy games with significant parity elements but also for broadening the resilience and efficiency of RL systems across diverse and complex environments.