Recently, I had an idea of a novel Deep RL algorithm that might perform better than existing algorithms such as DQN, TRPO, PPO, etc. However, I do not know of a website or a research paper that might gather/present the performance of all existing Deep RL algorithms on a set of known environments. So my question is, is there a known/standard place where one can find the current state-of-the-art performance of Deep RL algorithms?
Add a comment
|