New answers tagged

0 votes

Can DQN lead with discrete state spaces?

yes you can discretize whatever you want, though you'll have to deal with the consequences of that choice (aka it might work worse than the tabular method)
Alberto's user avatar
  • 1,885
0 votes

Can DQN lead with discrete state spaces?

Binning of inputs are of course possible but it is a balancing act that may never outperform a network operating on continuous values. Coarse binning may lose information necessary to accurately solve ...
foreverska's user avatar
0 votes

Is there a logical method of deducing an optimal batch size when training a Deep Q-learning agent with experience replay?

In my experience, exploration is always the challenge with RL, and I think about batch size a way of increasing exploration. What happens during training of an RL agent, is the policies entropy often ...
Duane's user avatar
  • 101
0 votes

What should I do, reinforcement learning agent gives different result on every train?

The problem is not that the algorithm is getting inconsistent results and you need to nail it down to one of the "good" strategies. It is instead that the algorithm is getting inconsistent ...
foreverska's user avatar
4 votes
Accepted

Does the DoubleDQN algorithm use a target network or two separate policies?

The canonical DoubleDQN uses the target network. I've not seen the first version used anywhere in the deep RL literature, but it looks like what one would do if they were to take the original Double Q-...
David's user avatar
  • 4,900
2 votes
Accepted

Can/should a reward function depend on something other than state in a DQN

Reward functions often depend on variables not present in the current state. Trading is the perfect example. Try as we might, we are unlikely to capture every variable necessary to perfectly predict ...
foreverska's user avatar
0 votes
Accepted

Use your own simulation to train a reinforcement learning multi-agent

An environment is not a magical concept in Reinforcement Learning (RL). When the textbooks were written on RL the python "gym" concept certainly did not exist much less during the time of ...
foreverska's user avatar
2 votes

CNN Input shape for DQN Q-calculating Network

CNNs have an inductive bias of locality. They work great on images because squares of inputs often are of an object. It is a hint to the ML algorithm that very far away pixels should not be ...
foreverska's user avatar

Top 50 recent answers are included