modurl 0.1.0

Modular reinforcement learning algorithms and utilities built on Candle
Documentation
# Summary


[Introduction](./introduction.md)

- [Getting Started]./getting-started.md
- [Core Concepts]./core-concepts.md
  - [Models, Policies, and Distributions]./models-policies-and-distributions.md
- [PPO]./ppo.md
  - [Understand a PPO Training Run]./understand-ppo-training.md
- [A2C]./a2c.md
- [Soft Actor-Critic]./sac.md
  - [Understand an SAC Training Run]./understand-sac-training.md
- [Deterministic Actor-Critic Training]./deterministic-actor-critic.md
  - [DDPG]./ddpg.md
  - [TD3]./td3.md
  - [Understand a Training Run]./understand-deterministic-actor-critic-training.md
- [Value-Based Training]./q-learning.md
  - [DQN]./dqn.md
  - [Double DQN]./ddqn.md
  - [Understand a Q-Learning Training Run]./understand-q-learning-training.md
- [Environments]./environments.md
  - [Environment Wrappers]./wrappers.md
  - [Use Vectorized Environments]./vectorized-environments.md
  - [Build a Custom Gym Environment]./custom-gym-environment.md
- [How-to Guides]./how-to-guides.md
  - [Run on CUDA or Metal]./run-on-cuda-or-metal.md