https://github.com/sarodyatawatta/hintrl
Hint assisted reinforcement learning
https://github.com/sarodyatawatta/hintrl
bipedalwalkerhardcore ensemble-model pets radio-astronomy reinforcement-learning sagecal soft-actor-critic
Last synced: 4 months ago
JSON representation
Hint assisted reinforcement learning
- Host: GitHub
- URL: https://github.com/sarodyatawatta/hintrl
- Owner: SarodYatawatta
- License: apache-2.0
- Created: 2022-10-14T08:29:13.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2024-10-05T14:08:56.000Z (8 months ago)
- Last Synced: 2025-01-14T03:17:35.715Z (5 months ago)
- Topics: bipedalwalkerhardcore, ensemble-model, pets, radio-astronomy, reinforcement-learning, sagecal, soft-actor-critic
- Language: Python
- Homepage:
- Size: 309 KB
- Stars: 1
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# hintRL
Reinforcement learning assisted by hints, code to accompany the preprint [Hint assisted reinforcement learning: an application in radio astronomy](https://arxiv.org/abs/2301.03933) and the review [Reinforcement learning](https://www.sciencedirect.com/science/article/pii/S2213133724000489).
## Bipedal Walker
See the files in bipedal_walker.
## Calibration
See [this link](https://github.com/SarodYatawatta/smart-calibration/tree/main/demixing_rl). Python version will be available soon.
## Model based RL (PETS)
see the files in model_based.
di 21 mei 2024 18:03:06 CEST