tspooner / rsrl / 100

Builds Branch Commit Type Ran Committer Via Coverage
100 rf-logging Add logging helper functions for stdout and files push tspooner travis-ci pending completion   set done
96 ft-multi_step_learning Correct importance sampling ratio calculation push tspooner travis-ci pending completion   set done
95 master Correct implementation of EpsilonGreedy Well that was embarrassing. In future, give tests even more attention! push tspooner travis-ci pending completion   set done
94 master Add logging helper functions for stdout and files push tspooner travis-ci pending completion   set done
93 master Add conversion function to Infinite dimension type push tspooner travis-ci pending completion   set done
92 master Minor cleanup in Trace enum push tspooner travis-ci pending completion   set done
91 master Merge pull request #6 from tspooner/ft-multi_step_learning Multi step learning algorithm push web-flow travis-ci pending completion   set done
90 master Correct importance sampling ratio calculation Pull #6 web-flow travis-ci pending completion   set done
89 ft-multi_step_learning Correct importance sampling ratio calculation push tspooner travis-ci pending completion   set done
87 ft-multi_step_learning Add first attempt at implementing Q(sigma) push tspooner travis-ci pending completion   set done
86 master Merge pull request #5 from tspooner/ft-traces Eligibility trace support push web-flow travis-ci pending completion   set done
85 master Merge branch 'master' into ft-traces Conflicts: src/agents/mod.rs Pull #5 web-flow travis-ci pending completion   set done
84 ft-traces Merge branch 'master' into ft-traces Conflicts: src/agents/mod.rs push tspooner travis-ci pending completion   set done
82 ft-traces Add TDLambda algorithm push tspooner travis-ci pending completion   set done
81 master Replace pi_target method with evaluate_policy The pi_target method wasn't well defined for on-policy control algorithms. It was just being used to evaluate a greedy policy during evaluation. For more clarity it has been replaced with a method eva... push tspooner travis-ci pending completion   set done