awjuliani/DeepRL-Agents resource

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

2279 stars · 820 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A collection of deep reinforcement learning agents implemented in TensorFlow as Jupyter notebooks, covering algorithms from Q-tables to A3C. It accompanies a Medium tutorial series and serves as an educational resource for learning RL.

Use cases

• learn reinforcement learning from scratch with worked examples
• understand how DQN and double dueling DQN work
• study policy gradient methods like vanilla policy networks
• see an A3C implementation for 3D environments like VizDoom
• explore exploration strategies such as Boltzmann and Bayesian dropout
• follow a tutorial series on deep RL with TensorFlow

When to choose

• you are learning deep RL and want readable, notebook-based implementations
• you want code paired with explanatory tutorial articles
• you need reference implementations of classic RL algorithms in TensorFlow 1.x

When to avoid

• you need a production-ready or maintained RL library
• you use modern TensorFlow 2.x or PyTorch
• you need the latest RL algorithms like PPO or SAC

Facets

learning-resource · maturity maintenance

machine-learning reinforcement-learning reinforcement-learning machine-learning tutorials python tensorflow jupyter-notebooks q-learning policy-gradients a3c dqn tutorial-series

Member repositories

For agents

markdown · JSON · MCP: product_card(name="awjuliani/DeepRL-Agents")