I am looking for an experienced Python developer with knowledge of reinforcement learning / Markov Decision Processes (MDP) to implement decision-making algorithms for an agent operating in a stochastic grid-world environment.
The task involves implementing and visualizing Value Iteration and Policy Iteration algorithms in a probabilistic maze environment.

The goal is to compute:

• Optimal policies
• State utilities
• Convergence behaviour of the algorithms

Clear visualizations and well-structured code are required.

Will need you to do revisions if required.

More details will be provided.

Contract duration of less than 1 month.

Mandatory skills:
Python, Writing, English