ajheshbasnet/reinforcement-learning-agents

a collection of advanced reinforcement learning (rl) agents and implementations, including dqn, actor-critic, ppo, dpo, and more. provides reference code, algorithmic insights, and setups for research, experimentation, and benchmarking of state-of-the-art rl methods.

29
/ 100
Experimental

This collection provides clear, self-contained examples of core reinforcement learning algorithms like DQN and PPO. It takes in algorithm definitions and environment setups, producing training metrics like reward curves and loss plots, visualized through Weights & Biases. It's ideal for machine learning researchers, students, or practitioners who need to understand, experiment with, or benchmark advanced RL methods.

Use this if you need to deeply understand how specific reinforcement learning algorithms work, experiment with their implementations, or benchmark their performance in a straightforward manner.

Not ideal if you're looking for a high-level API or a production-ready RL framework with extensive abstraction layers.

machine-learning-research reinforcement-learning algorithm-benchmarking ai-model-experimentation policy-optimization
No License No Package No Dependents
Maintenance 13 / 25
Adoption 6 / 25
Maturity 5 / 25
Community 5 / 25

How are scores calculated?

Stars

19

Forks

1

Language

Jupyter Notebook

License

Last pushed

Mar 22, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/ajheshbasnet/reinforcement-learning-agents"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.