jlm429/bettermdptools issues and pull requests

#23 - Returned the number of iterations needed to converge for VI and PI

Pull Request - State: closed - Opened by andyrao408 3 months ago - 1 comment

#22 - Randomly choose between equally good actions

Pull Request - State: closed - Opened by abouelsaadat 3 months ago

#21 - GridSearch - Return highest reward and params

Pull Request - State: closed - Opened by fidmor89 3 months ago

#20 - feat: make show optional

Pull Request - State: closed - Opened by dcangulo 3 months ago

#19 - Taxi-v3 infinite loop in policy_iteration

Issue - State: open - Opened by jblackwood12 3 months ago

#18 - WARN: env.P to get variables from other wrappers is deprecated

Issue - State: open - Opened by MatthewFletcher 3 months ago

#17 - plots Q-learning wrapper

Issue - State: closed - Opened by jlm429 8 months ago - 1 comment

#16 - example plots are not resizing

Issue - State: closed - Opened by jlm429 8 months ago - 1 comment

#15 - Represent policies with dictionaries for efficiency

Pull Request - State: closed - Opened by leeykang 8 months ago - 2 comments

#14 - Adding .pickle extension to blackjack-envP file

Pull Request - State: closed - Opened by audols 8 months ago - 1 comment

#13 - examples/blackjack-envP doesn't install by default due to lack of .py extension

Issue - State: closed - Opened by audols 8 months ago

#12 - not able to import after conda install

Issue - State: closed - Opened by jlm429 9 months ago - 1 comment

#11 - pygame issues

Issue - State: closed - Opened by jlm429 12 months ago - 2 comments

#10 - SARSA doc init_epsilon

Issue - State: closed - Opened by jlm429 about 1 year ago - 1 comment

#9 - bug fix: index out of bounds

Pull Request - State: closed - Opened by zbalda about 1 year ago

#8 - Fix README.md example - add needed imports

Issue - State: closed - Opened by e-loughlin about 1 year ago - 1 comment

#7 - fix q-learning doc for init epsilon

Pull Request - State: closed - Opened by cbhyphen about 1 year ago

#6 - off by one bug

Issue - State: closed - Opened by jlm429 over 1 year ago - 2 comments

#5 - Documentation addition to the relevant scripts

Pull Request - State: closed - Opened by GaganCodes over 1 year ago

#4 - Not working with latest gym version

Issue - State: closed - Opened by jlm429 over 1 year ago - 1 comment

#3 - Updated Policy Iteration such that Policy Evaluation starts with previous V-values, not zeros

Pull Request - State: closed - Opened by Tim-K-DFW over 1 year ago

#2 - Policy iteration - can be improved to run faster and aligned with Sutton-Barto

Issue - State: closed - Opened by Tim-K-DFW over 1 year ago - 1 comment

#1 - README - minor correction