https://github.com/kohlerhector/ibmdp-py

Implementation of Iterative Bounding Markov Decision Processes (Topin et. al. 2021)
https://github.com/kohlerhector/ibmdp-py

reinforcement-learning

Last synced: about 8 hours ago
JSON representation

Implementation of Iterative Bounding Markov Decision Processes (Topin et. al. 2021)

• Host: GitHub
• URL: https://github.com/kohlerhector/ibmdp-py
• Owner: KohlerHECTOR
• Created: 2024-07-22T14:11:42.000Z (4 months ago)
• Default Branch: main
• Last Pushed: 2024-07-23T10:23:40.000Z (4 months ago)
• Last Synced: 2024-07-23T17:18:17.654Z (4 months ago)
• Topics: reinforcement-learning
• Language: Python
• Homepage: https://arxiv.org/abs/2102.13045
• Size: 2.93 KB
• Stars: 1
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Iterative Bounding Markov Decision Processes

Implementation of [IBMDPs](https://arxiv.org/abs/2102.13045).

Just copy the ```gymnasium``` environment from here [ibmdp](ibmdp/ibmdp.py).

```python

from stable_baselines3 import PPO

from gymnasium import make

from gymnasium.wrappers.time_limit import TimeLimit

from ibmdp import IBMDP

env = make("CartPole-v1")

env = IBMDP(env, zeta=0, info_gathering_actions=[(0,0)])

env = TimeLimit(env, 1000)

model = PPO("MlpPolicy", env, verbose=1)

model.learn(1e5)

```