Average-Reward Maximum Entropy Reinforcement Learning for Underactuated Double Pendulum Tasks
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914948779606016 |
|---|---|
| author | Choe, Jean Seong Bjorn Choi, Bumkyu Kim, Jong-kook |
| author_facet | Choe, Jean Seong Bjorn Choi, Bumkyu Kim, Jong-kook |
| contents | This report presents a solution for the swing-up and stabilisation tasks of the acrobot and the pendubot, developed for the AI Olympics competition at IROS 2024. Our approach employs the Average-Reward Entropy Advantage Policy Optimization (AR-EAPO), a model-free reinforcement learning (RL) algorithm that combines average-reward RL and maximum entropy RL. Results demonstrate that our controller achieves improved performance and robustness scores compared to established baseline methods in both the acrobot and pendubot scenarios, without the need for a heavily engineered reward function or system model. The current results are applicable exclusively to the simulation stage setup. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_08938 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Average-Reward Maximum Entropy Reinforcement Learning for Underactuated Double Pendulum Tasks Choe, Jean Seong Bjorn Choi, Bumkyu Kim, Jong-kook Robotics Machine Learning This report presents a solution for the swing-up and stabilisation tasks of the acrobot and the pendubot, developed for the AI Olympics competition at IROS 2024. Our approach employs the Average-Reward Entropy Advantage Policy Optimization (AR-EAPO), a model-free reinforcement learning (RL) algorithm that combines average-reward RL and maximum entropy RL. Results demonstrate that our controller achieves improved performance and robustness scores compared to established baseline methods in both the acrobot and pendubot scenarios, without the need for a heavily engineered reward function or system model. The current results are applicable exclusively to the simulation stage setup. |
| title | Average-Reward Maximum Entropy Reinforcement Learning for Underactuated Double Pendulum Tasks |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2409.08938 |