-
-
Notifications
You must be signed in to change notification settings - Fork 34
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Add reinforcement learning #175
Merged
christianechevarria
merged 15 commits into
liquidcarrot:add-reinforcement-learning
from
raimannma:add-reinforcement-learning
Nov 1, 2019
Merged
Add reinforcement learning #175
christianechevarria
merged 15 commits into
liquidcarrot:add-reinforcement-learning
from
raimannma:add-reinforcement-learning
Nov 1, 2019
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
adding a new util-class "Window", works similar as the Java ArrayDeque add training mode for the DQN much improvement in performance allow mulit-hidden layers
The sign for the epsilon action comparison was reversed. Epsilon should begin as a high number which will lead to high exploration at first. By exploring at a high rate the agent can discover new states instead of following its judgement (poor at first) about what the best state is and with a decay function over time epsilon is decreased which then leads the agent to trust its judgement more as it has more experiences.
To be as beginner friendly as possible, we change 'epsilon'-based property names to 'explore'. We do this because the people aware of epsilon's meaning should be able to know that explore is an equivalent term, but the reverse may not be true
To be as beginner friendly as possible, we change 'epsilon'-based property names to 'explore'. We do this because the people aware of epsilon's meaning should be able to know that explore is an equivalent term, but the reverse may not be true
christianechevarria
approved these changes
Nov 1, 2019
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Fully implemented DQN
More test methods are needed!