# Starter Kit

## Docs

- [Reinforcement Learning Agents](https://pycrm.xyz/core-concepts/agents.md): Agent implementations that leverage Counting Reward Machines
- [RMs & CRMs](https://pycrm.xyz/core-concepts/automata.md): Creating structured task specifications for reinforcement learning
- [Cross-Product Environments](https://pycrm.xyz/core-concepts/cross-products.md): Combining ground environments with reward machines to create learning tasks
- [Labelling Functions](https://pycrm.xyz/core-concepts/labelling-functions.md): Converting low-level observations to high-level symbolic events
- [Installation](https://pycrm.xyz/installation.md): Install and set up Counting Reward Machines
- [Introduction](https://pycrm.xyz/introduction.md): Learn about Reward Machines (RMs), Counting Reward Machines (CRMs), and their applications in reinforcement learning
- [Quick Start](https://pycrm.xyz/quickstart.md): Get started with Reward Machines and Counting Reward Machines in minutes
- [6 - Counterfactual Q-Learning](https://pycrm.xyz/worked-examples/letter-env/counterfactual-q-learning.md): Accelerate learning with counterfactual experiences using RM/CRMs
- [3 - Reward Machine](https://pycrm.xyz/worked-examples/letter-env/crm.md): Defining rewards based on symbolic event sequences
- [4 - Cross-Product](https://pycrm.xyz/worked-examples/letter-env/cross-product.md): Get started with Counting Reward Machines in minutes
- [1 - Ground Environment](https://pycrm.xyz/worked-examples/letter-env/ground-environment.md): Understanding the Letter World grid environment
- [2 - Labelling Function](https://pycrm.xyz/worked-examples/letter-env/labelling-function.md): Converting environment states to symbolic events
- [5 - Q-Learning in Letter World](https://pycrm.xyz/worked-examples/letter-env/q-learning.md): Training an agent with Q-Learning in the Letter World environment
- [Setup & Overview](https://pycrm.xyz/worked-examples/letter-env/setup.md): How to set up and run the PyCRM examples

## OpenAPI Specs

- [openapi](https://pycrm.xyz/api-reference/openapi.json)

## Optional

- [Code](https://github.com/TristanBester/counting-reward-machines)
- [Paper](https://arxiv.org/abs/2312.11364)
- [Demo](https://crm.tristanbester.xyz)