https://github.com/noblessecoder/reinforcei
Implementation of various Reinforcement Learning Agents
https://github.com/noblessecoder/reinforcei
machine-learning openai-gym python3 reinforcement-learning reinforcement-learning-agent reinforcement-learning-algorithms
Last synced: 3 months ago
JSON representation
Implementation of various Reinforcement Learning Agents
- Host: GitHub
- URL: https://github.com/noblessecoder/reinforcei
- Owner: NoblesseCoder
- License: mit
- Created: 2020-04-17T06:52:26.000Z (about 5 years ago)
- Default Branch: master
- Last Pushed: 2020-08-15T20:34:13.000Z (almost 5 years ago)
- Last Synced: 2025-01-21T08:31:48.248Z (5 months ago)
- Topics: machine-learning, openai-gym, python3, reinforcement-learning, reinforcement-learning-agent, reinforcement-learning-algorithms
- Language: Python
- Size: 193 KB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Reinforcei
The repository contains implementation of various Reinforcement Learning algorithms.
### Prerequisite Installations
1. [Install Gym](https://gym.openai.com/docs/)
2. [Install gym-karmedbandits](https://github.com/NoblesseCoder/gym-karmedbandits)
### Basic Agents
1. [Random agent ](./agents/tabular/agent.py)
2. [Human agent](./agents/tabular/human_agent.py)
3. [ε-greedy agent](./agents/tabular/epsilon_greedy_agent.py) [(Demo)](./demos/stationary_MAB_problem.py)
4. [UCB greedy agent](./agents/tabular/upper_confidence_bound_agent.py) [(Demo)](./demos/stationary_MAB_problem.py)
### References
[1] [Reinforcement Learning, Second Edition: An Introduction)](https://mitpress.mit.edu/books/reinforcement-learning-second-edition)