On-Policy Optimization of ANFIS Policies Using Proximal Policy Optimization
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908433313169408 |
|---|---|
| author | Shankar, Kaaustaaub Louw, Wilhelm Cohen, Kelly |
| author_facet | Shankar, Kaaustaaub Louw, Wilhelm Cohen, Kelly |
| contents | We present a reinforcement learning method for training neuro-fuzzy controllers using Proximal Policy Optimization (PPO). Unlike prior approaches that used Deep Q-Networks (DQN) with Adaptive Neuro-Fuzzy Inference Systems (ANFIS), our PPO-based framework leverages a stable on-policy actor-critic setup. Evaluated on the CartPole-v1 environment across multiple seeds, PPO-trained fuzzy agents consistently achieved the maximum return of 500 with zero variance after 20000 updates, outperforming ANFIS-DQN baselines in both stability and convergence speed. This highlights PPO's potential for training explainable neuro-fuzzy agents in reinforcement learning tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_01039 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | On-Policy Optimization of ANFIS Policies Using Proximal Policy Optimization Shankar, Kaaustaaub Louw, Wilhelm Cohen, Kelly Machine Learning Artificial Intelligence We present a reinforcement learning method for training neuro-fuzzy controllers using Proximal Policy Optimization (PPO). Unlike prior approaches that used Deep Q-Networks (DQN) with Adaptive Neuro-Fuzzy Inference Systems (ANFIS), our PPO-based framework leverages a stable on-policy actor-critic setup. Evaluated on the CartPole-v1 environment across multiple seeds, PPO-trained fuzzy agents consistently achieved the maximum return of 500 with zero variance after 20000 updates, outperforming ANFIS-DQN baselines in both stability and convergence speed. This highlights PPO's potential for training explainable neuro-fuzzy agents in reinforcement learning tasks. |
| title | On-Policy Optimization of ANFIS Policies Using Proximal Policy Optimization |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2507.01039 |