Skip to main content
added 106 characters in body
Source Link
nbro
  • 41.4k
  • 12
  • 114
  • 205

MNIST (along with CIFAR) may be the "Hello World" of supervised learning for image classification, but it is definitely not the "Hello World" of all machine learning techniques, given that RL is also part of ML and MNIST is definitely not the "Hello World" of RL.

I don't think there is a single "Hello World" problem for RL. However, if you are looking for simple problems (or environments) that are usually used as baselines to assess the quality of RL agents, then I would say that the simple grid worlds where you need to move from one place to the other, the CartPole, MountainCar, Pendulum or other environments listed here are often used.

The environment that you choose to train and test your RL agent depends on your goals. For example, if you designed an algorithm that is supposed to deal with continuous action spaces, then an environment where you can take only a discrete number of actions may not be a good option.

The mentioned environments are very simple (i.e. toy problems). In my opinion, we need more serious environments that can show the applicability of RL to other areas other than (relatively simple) games.

MNIST (along with CIFAR) may be the "Hello World" of supervised learning for image classification, but it is definitely not the "Hello World" of all machine learning techniques, given that RL is also part of ML and MNIST is definitely not the "Hello World" of RL.

I don't think there is a single "Hello World" problem for RL. However, if you are looking for simple problems (or environments) that are usually used as baselines to assess the quality of RL agents, then I would say that the simple grid worlds where you need to move from one place to the other, the CartPole, MountainCar, Pendulum or other environments listed here are often used.

The environment that you choose to train and test your RL agent depends on your goals. For example, if you designed an algorithm that is supposed to deal with continuous action spaces, then an environment where you can take only a discrete number of actions may not be a good option.

MNIST (along with CIFAR) may be the "Hello World" of supervised learning for image classification, but it is definitely not the "Hello World" of all machine learning techniques, given that RL is also part of ML and MNIST is definitely not the "Hello World" of RL.

I don't think there is a single "Hello World" problem for RL. However, if you are looking for simple problems (or environments) that are usually used as baselines to assess the quality of RL agents, then I would say that the simple grid worlds where you need to move from one place to the other, the CartPole, MountainCar, Pendulum or other environments listed here are often used.

The environment that you choose to train and test your RL agent depends on your goals. For example, if you designed an algorithm that is supposed to deal with continuous action spaces, then an environment where you can take only a discrete number of actions may not be a good option.

The mentioned environments are very simple (i.e. toy problems). In my opinion, we need more serious environments that can show the applicability of RL to other areas other than (relatively simple) games.

deleted 2 characters in body
Source Link
nbro
  • 41.4k
  • 12
  • 114
  • 205

MNIST (along with CIFAR) may be the "Hello World" of supervised learning for image classification, but it is definitely not the "Hello World" of all machine learning techniques, given that RL is also part of ML and MNIST is definitely not the "Hello World" of RL.

I don't think there is a single "Hello World" problem for RL. However, if you are looking for simple problems (or environments) that are usually used as baselines to assess the quality of RL agents, then I would say that the simple grid worlds where you need to move from one place to the other, the CartPole, MountainCar, Pendulum or other environments listed here are often used.

The environment that you choose to train and test your RL agent depends on your goals. For example, if you designed an algorithm that is supposed to deal with continuous action spaces, then thean environment where you can take only a discrete grid worldsnumber of actions may not be a good baselineoption.

MNIST may be the "Hello World" of supervised learning for image classification, but it is definitely not the "Hello World" of all machine learning techniques, given that RL is also part of ML and MNIST is definitely not the "Hello World" of RL.

I don't think there is a single "Hello World" problem for RL. However, if you are looking for simple problems (or environments) that are usually used as baselines to assess the quality of RL agents, then I would say that the simple grid worlds where you need to move from one place to the other, the CartPole, MountainCar, Pendulum or other environments listed here are often used.

The environment that you choose to train and test your RL agent depends on your goals. For example, if you designed an algorithm that is supposed to deal with continuous action spaces, then the discrete grid worlds may not be a good baseline.

MNIST (along with CIFAR) may be the "Hello World" of supervised learning for image classification, but it is definitely not the "Hello World" of all machine learning techniques, given that RL is also part of ML and MNIST is definitely not the "Hello World" of RL.

I don't think there is a single "Hello World" problem for RL. However, if you are looking for simple problems (or environments) that are usually used as baselines to assess the quality of RL agents, then I would say that the simple grid worlds where you need to move from one place to the other, the CartPole, MountainCar, Pendulum or other environments listed here are often used.

The environment that you choose to train and test your RL agent depends on your goals. For example, if you designed an algorithm that is supposed to deal with continuous action spaces, then an environment where you can take only a discrete number of actions may not be a good option.

deleted 2 characters in body
Source Link
nbro
  • 41.4k
  • 12
  • 114
  • 205

MNIST may be the "Hello World!"World" of supervised learning for image classification, but it is definitely not the "Hello World" of all machine learning techniques, given that RL is also part of ML and "MNIST"MNIST is definitely not the "Hello World" of RL.

I don't think there is a single "Hello World" problem for RL. However, if you are looking for simple problems (or environments) that are usually used as baselines to assess the quality of RL agents, then I would say that the simple grid worlds where you need to move from one place to the other, the CartPole, MountainCar, Pendulum or other environments listed here are often used.

The environment that you choose to train and test your RL agent depends on your goals. For example, if you designed an algorithm that is supposed to deal with continuous action spaces, then the discrete grid worlds may not be a good baseline.

MNIST may be the "Hello World!" of supervised learning for image classification, but it is definitely not the "Hello World" of all machine learning techniques, given that RL is also part of ML and "MNIST" is definitely not the "Hello World" of RL.

I don't think there is a single "Hello World" problem for RL. However, if you are looking for simple problems that are usually used as baselines to assess the quality of RL agents, then I would say that the simple grid worlds where you need to move from one place to the other, the CartPole, MountainCar, Pendulum or other environments listed here are often used.

MNIST may be the "Hello World" of supervised learning for image classification, but it is definitely not the "Hello World" of all machine learning techniques, given that RL is also part of ML and MNIST is definitely not the "Hello World" of RL.

I don't think there is a single "Hello World" problem for RL. However, if you are looking for simple problems (or environments) that are usually used as baselines to assess the quality of RL agents, then I would say that the simple grid worlds where you need to move from one place to the other, the CartPole, MountainCar, Pendulum or other environments listed here are often used.

The environment that you choose to train and test your RL agent depends on your goals. For example, if you designed an algorithm that is supposed to deal with continuous action spaces, then the discrete grid worlds may not be a good baseline.

Source Link
nbro
  • 41.4k
  • 12
  • 114
  • 205
Loading