These are javascript implementations of Arthur Juliani's Simple Reinforcement Learning with Tensorflow series, built using Tensorflow.js.
Part 2 — Policy-Based Agents
Part 3 — Model-Based RL
Part 4 — Deep Q-Networks and Beyond
Part 5 — Visualizing an Agent’s Thoughts and Actions
Part 6 — Partial Observability and Deep Recurrent Q-Networks
Part 7 — Action-Selection Strategies for Exploration
Part 8 — Asynchronous Actor-Critic Agents (A3C)