markusdumke / reinforcelearn

R Package for Reinforcement Learning

https://markusdumke.github.io/reinforcelearn/

markusdumke/reinforcelearn Issues

Some help setting up a toy example: where to define the action space?
Updated 5 years ago
Errors in the Agents vignette
Updated 5 years ago7
an error reported using kera neural network model
Updated 5 years ago
interact with OpenAI gyms
Updated 5 years ago
Fix issues with new R Version 3.6.0
Closed 6 years ago1
keras training is too slow
Updated 6 years ago2
qlearning et all: no arg check on class for first arg. that must be an RL environment
Closed 7 years ago
fun.approx = "neural.network" uninformative error
Closed 7 years ago
?qlearning et al are missing precise docs for return value
Closed 7 years ago
env printer seems to be not informative enough
Closed 7 years ago1
can we visualize policy steps and what happens during learning?
Closed 7 years ago1
it would be nice if states and actions have string names
Closed 7 years ago1
sarsa on mountaincar leads to uninformative error - because we have no func approx
Closed 7 years ago
more uninformative error
Closed 7 years ago
is there an R6 object to represent a policy?
Closed 7 years ago1
can we have a better startup procedure for ai gym?
Closed 7 years ago1
what happens in eg mountaincar if the car is not pushed to the top?
Closed 7 years ago1
how can i run my learned policy
Closed 7 years ago1
Error when calling `makeEnvironment` after start of Rstudio
Closed 7 years ago5
README: we should copy the install instructs for openai gym and keras to our readme
Updated 7 years ago
qlearning et al: preprocessState docs
Updated 7 years ago
Double Q-Learning not working
Closed 8 years ago
Implement Policy Iteration and Value Iteration
Closed 8 years ago
Expected Sarsa not giving the expected results on gridworld
Closed 8 years ago
Implement MC control
Closed 8 years ago
Implement algorithms with value-function approximation
Closed 8 years ago
MonteCarlo Control with Exploring Starts not working
Closed 8 years ago
Test for Sarsa fails
Closed 8 years ago
Implement lambda version of sarsa
Closed 8 years ago
TD not working
Closed 8 years ago
predictMC not working
Closed 8 years ago
implement gridworld as R6 class
Closed 8 years ago
fix bug in gridworld.R
Closed 8 years ago