2
votes
Accepted
What happens when the agent faces a state that never before encountered?
Having too many states to actually visit is a common problem in RL. This is exactly why we often use function approximation. If you replace your q table with a good function approximator such as a ...
- 2,020
2
votes
Should I apply normalization to the observations in deep reinforcement learning?
The use of normalisation in neural networks and many other (but not all - decision trees are a notable exception) machine learning methods, is to improve the quality of the parameter space with ...
- 26.6k
1
vote
When should discretization of observations be considered?
I believe that discretizing the action/state space when using function approximators like NN is only acceptable when losing information is acceptable. Why would you discretize an observation, for ...
- 81
1
vote
Accepted
Are multi agent or self-play environments always automatically POMDPs?
Generally, "perfect information" is not a formal trait of MDPs. There is a concept of the Markov property, but it only loosely coincides with "perfect information". For instance it ...
- 26.6k
1
vote
Should I apply normalization to the observations in deep reinforcement learning?
On creating custom environments:
... always normalize your observation space when you can, i.e., when you know the boundaries
(From stable-baselines)
You could normalize them as part of the ...
- 511
1
vote
Scrabble rack observation with MuZero
Use one hot encoding for each position, shape $(7, 27)$.
Stack these two dimensions, shape $(189)$.
Tile (replicate) this vector into images of the same resolution, now shape $(15, 15, 189)$
Stack ...
- 136
1
vote
What happens when the agent faces a state that never before encountered?
I will try to explain this problem with the very tangible example of chess. In chess, the number of possible states is any configuration that you can make with the pieces on the board. So, the ...
- 808
Only top scored, non community-wiki answers of a minimum length are eligible