Experiments Results and Data MartestPipeline 'Constructing a language for testing Reinforcement Learning programs using NLP techniques'

In the following repository, you will find the results of the execution of the Martest-Pipeline for agents in LunarLander and CartPole. The repository includes the abstract classes, the conditioned transformer models, and the corresponding forecast results. Additionally, it contains the agents' logs and the outcomes of their executions, which were further analyzed through statistical studies.