# A new soft computing method for integration of expert's knowledge in reinforcement learn-ing problems

arXiv: https://arxiv.org/abs/2106.07088 · HTML: https://mlsanity.com/paper/2106.07088/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 34 references that are in the map.
- First posted on arXiv 13 Jun 2021.

## Builds on (most cited first, 10 of 10)

- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Bridging the Gap Between Value and Policy Based Reinforcement Learning](https://mlsanity.com/paper/1702.08892/) (2017)
- [A Survey and Critique of Multiagent Deep Reinforcement Learning](https://mlsanity.com/paper/1810.05587/) (2018)
- [A Survey of Reinforcement Learning Informed by Natural Language](https://mlsanity.com/paper/1906.03926/) (2019)
- [Algorithms for multi-armed bandit problems](https://mlsanity.com/paper/1402.6028/) (2014)
- [Generalizing Skills with Semi-Supervised Reinforcement Learning](https://mlsanity.com/paper/1612.00429/) (2016)
- [KoGuN: Accelerating Deep Reinforcement Learning via Integrating Human Suboptimal Knowledge](https://mlsanity.com/paper/2002.07418/) (2020)
- [Semi-Supervised Off Policy Reinforcement Learning](https://mlsanity.com/paper/2012.04809/) (2020)
- [Continuous Emotion Recognition during Music Listening Using EEG Signals: A Fuzzy Parallel Cascades Model](https://mlsanity.com/paper/1910.10489/) (2019)
- [Constrained-Space Optimization and Reinforcement Learning for Complex Tasks](https://mlsanity.com/paper/2004.00716/) (2020)

## Abstract (arXiv)

This paper proposes a novel fuzzy action selection method to leverage human knowledge in reinforcement learning problems. Based on the estimates of the most current action-state values, the proposed fuzzy nonlinear mapping as-signs each member of the action set to its probability of being chosen in the next step. A user tunable parameter is introduced to control the action selection policy, which determines the agent's greedy behavior throughout the learning process. This parameter resembles the role of the temperature parameter in the softmax action selection policy, but its tuning process can be more knowledge-oriented since this parameter reflects the human knowledge into the learning agent by making modifications in the fuzzy rule base. Simulation results indicate that including fuzzy logic within the reinforcement learning in the proposed manner improves the learning algorithm's convergence rate, and provides superior performance.