* Minor modifications in planning_angelic_search.ipynb and knowledge_FOIL.ipynb notebooks.

* Modified FOIL_container

* Added unit tests for FOIL_container functions

* Added knowledge_current_best notebook

* Added knowledge_FOIL notebook

* Added knowledge_version_space notebook

* Added images for knowledge_FOIL notebook

* knowledge.ipynb replaced by knowledge_current_best.ipynb, knowledge_version_space.ipynb, knowledge_FOIL.ipynb

* modify knowledge.py

* Added tests for online dfs agent

* Minor formatting fixes

* Completed notebook sections

* Updated README.md

* Fixed a test

* Added new algorithms to display_visual notebook function

* Added RBFS visualization

* Added notebook section for DTAgentProgram

* Updated README.md

* Minor

* Added TODO to fix pomdp tests

* Added notebook section on AC3

* Added doctests to agents.py

* Fixed pomdp tests

* Fixed a doctest

* Fixed pomdp test

* Added doctests for rl.py

* Fixed NameError in rl.py doctests

* Fixed NameError in rl.py doctests

* Minor fixes

* Minor fixes

* Fixed ImportErrors

* Fixed all doctests

* created notebooks for GraphPlan, Total Order Planner and Partial Order Planner

* Added hierarchical search and tests

* Created notebook planning_hierarchical_search.ipynb

* Added making progress and tests, minor changes in decompose

* image for planning_hierarchical_search.ipynb

* Added angelic search to planning code

* Added unit tests for angelic search

* Created notebook planning_angelic_search.ipynb

* Fixed refinements function for HLAs

* Formatting fixes

* Added runtime comparisons of algorithms

* Added tests

* Updated README.md

* Added HMM explanation and contents tab

* Added section on fixed lag smoothing

* Added notebook sections on particle filtering and monte carlo localization

* Updated README.md

* Minor formatting fix

* Added decision networks and information gathering agent

* Added notebook sections for decision networks and information gathering agent

* Updated README.md

* Added POMDP value iteration

* Added plot_pomdp_utility function

* Added tests for pomdp-value-iteration

* Updated README.md

* Fixed notebook import

* Changed colors

* Added notebook sections for POMDP and pomdp_value_iteration

* Fixed notebook parsing error

* Replace pomdp.ipynb

* Updated README.md

* Fixed line endings

* Fixed line endings

* Fixed line endings

* Fixed line endings

* Removed numpy dependency

* Added docstrings

* Fix tests

* Added a test for pomdp_value_iteration

* Remove numpy dependencies from mdp.ipynb

* Added POMDP to mdp_apps.ipynb

* Added PartialOrderPlanner

* Added doctests

* Fix doctests

* Added tests for PartialOrderPlanner methods

* Added test for PartialOrderPlanner

* Rerun planning.ipynb

* Added notebook section for TotalOrderPlanner

* Added image

* Added notebook section for PartialOrderPlanner

* Updated README.md

* Refactor double tennis problem

* Refactored test for double_tennis_problem

* Updated README.md

* Added notebook sections for job_shop_problem and double_tennis_problem

* Updated README.md

* Fixed refinements example

* Added go_to_sfo problem

* Rename TotalOrderPlanner

* Renamed PDDL to PlanningProblem

* test case for zebra problem

* Revert "Merge remote-tracking branch 'upstream/master'"

This reverts commit 5ceab1a27ff73b410200c2f84d22e0a1d79b6fbe, reversing
changes made to 34997e48547a57939d568f170c60e442c2d54db5.

* discarded HEAD changes for merge

* added ensemble_learner jpeg

* updated travis and search

* Added logarithmic learner in nlp_apps (#890)

* Remove zebra tests

* revised Bayes learner explanation

* added missing SimpleReflexAgent from upstream

* Refactored HLA

* Refactors

* Refactored broken tests

* Cleaned up duplicated code

* Cleaned up duplicated code

* Added TotalOrderPlanner

* Linearize helper function

* Added tests for TotalOrderPlanner

* Readd sussman anomaly test

* Added a line to child node

`child_node` method of `Node` uses the `problem.result` which returns normally a state not a node according to its docstring in `Problem`. Naming the variable `next_node` can be confusing to users when it actually refers to a resulting state.

* Update search.py

* Update search.py

* PDDLs and Actions can now be defined using Exprs as well as Strings

* Minor refactors

* Add stochastic game class

* Update backgammon class

* Update Expectiminimax

* Fix lint issues

* Correct compute_utility function

should be '# Body of alphabeta_search:'

* Added MDP2 class

* Updated loop termination condition in value_iteration

* GraphPlan fixed

* Updated test_planning.py

* Added test for spare_tire

* Added test for graphplan

* Added shopping problem

* Added tests for shopping_problem

* Updated README.md

* Refactored planning notebook

* Completed shopping problem

* Refactors

* Updated notebook

* Updated test_planning.py

* Removed doctest temporarily

* Added planning graph image

* Added section on GraphPlan

* Updated README.md

* corrected cell type

* fixed umbrella_prior not defined error

* minor changes

* Resolve recursion issue in Backgammon class

* Handle empty action list in player functions

* Add play_game method for backgammon

* Refactor functions

* Update argmax function call

* added have_cake_and_eat_cake_too

* renamed effect_neg to effect_rem

* added have_cake_and_eat_cake_too to readme

* added details to Problems in planning.ipynb

Added more information for the problems Air Cargo, Spare Tire, Three Block Tower, Have Cake and Eat Cake Too.

* removed a test from planning.py

A test for three block tower problem is written here. I have removed it.

* Style fixes

* minor style fix

* fixed a typo

* minor fixes

some sentence issues

* minor changes

* minor fixes

* refactored changes

* added DLS and IDS to readme

* deleting

* reuploading

* Added linear learner in learning.ipynb

* Update learning.ipynb

* Update learning.ipynb

* Update learning.ipynb

* Added ensemble learner in learning.ipynb

* Added ensemble_learner.jpg

* Update learning.ipynb

* Update learning.ipynb

* define plan_route, plan_shot and refactor code

* minor changes

* Added PlanRoute Problem class

* update plan_route

return list of actions ( node.solution() ) instead of node itself in plan_route

* Added Depth Limited Search in search.ipynb

* Made changes in depth limited search

* added test case for CYK_parse

* added testcase for CYK_parse

* corrected spacing

* fixed issues like alignment, missing comma etc.

* test case for double tennis problem

* Update planning.py

removed commented print statements.

* Correction in the formula for mean square error

* Added cross-entropy loss

* Test case for cross-entropy loss

* Decimal point mistake

* Added spaces around = and ==