New answers tagged

1

You don't need to manage negative rewards separately, if you implemented the algorithm correctly it will work regardless if the rewards are negative or not. You seem to be using rewards for the loss but you should be using the return which is the sum of the rewards for some state action pair from that point until the end of trajectory. You also seem to be ...


0

although I have seen RL solutions to this problem, (those I saw) fail to realize that the state of mastermind is not observable, as there is the "secret" we're trying to guess. mastermind is best approached as a constraint satisfaction problem, along the lines described by Neil Slater. The whole trick is to realize that you can eliminate options from the "...


0

You could possibly apply neural networks, reinforcement learning to summarise results of previous choices (what you are calling context) and use score predictions to suggest the next turn's guess. However, the game of Mastermind has a small search space and it is possible to process this "context" more directly by refining a set of guesses. This will be much ...


0

Many people who are interested in machine learning aren't professional programmers. For example there are mathematicians who work on differential equations and there are physicists who work on stochastic processes. These people aren't programmers. So using a language like C++ which is hard to learn is only detrimental to their works. And also creating a ...


0

It might be that the large labels dominate the loss value, so the model pays more attention to them. You could use an L1 loss rather than an L2 loss, such that the predictions get pulled towards each label equally rather than being pulled more strongly when the label is further away from the prediction. There may also be a data imbalance, i.e. you train on ...


0

One option is normalizing your data. In particular, min-max feature scaling to bring all values into the range [0,1] is particularly useful with gradient descent.


Top 50 recent answers are included