New answers tagged

2 votes

Reward design or Inverse reinforcement learning?

It depends on the domain you are in. Inverse RL (IRL) would be most advantageous in domains in which: It's hard to specify the reward by hand: for example, it would be hard to hand-specify a reward ...
user avatar
  • 170
3 votes

How to deal with small reward values

The numbers that a value-based neural network will predict are usually based on expected returns (sum of rewards by end of an episode, or a discounted infinite sum), although in some cases they might ...
user avatar
  • 24.5k
1 vote

What happens with policy gradient methods if rewards are differentiable?

To elaborate on the edit made by Kostya above, the value that the rewards take on are governed by the transitional dynamics which are a part of the environment i.e. not affected by the policy. E.g. ...
user avatar

Top 50 recent answers are included