Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / markkho/msdm issues and pull requests
#79 - Fix issue where A* ignored subsequent visits to states that could have improved plans.
Pull Request -
State: closed - Opened by cgc over 1 year ago
#78 - A*: Throw error when heuristic is not admissible
Issue -
State: closed - Opened by cgc over 1 year ago
- 3 comments
#77 - Bidirectional search
Pull Request -
State: closed - Opened by Reeche over 1 year ago
#76 - Fix tie-breaking
Pull Request -
State: closed - Opened by markkho over 1 year ago
#75 - A* clean up
Pull Request -
State: closed - Opened by markkho over 1 year ago
#74 - A* LIFO/FIFO options
Issue -
State: closed - Opened by markkho over 1 year ago
- 1 comment
#73 - Astar refactor
Pull Request -
State: closed - Opened by markkho over 1 year ago
#72 - Implicit Distribution
Pull Request -
State: closed - Opened by markkho almost 2 years ago
#71 - Cython implementations of tabular MDPs and algorithms
Pull Request -
State: open - Opened by markkho almost 2 years ago
#70 - Options framework
Pull Request -
State: closed - Opened by markkho almost 2 years ago
#69 - Reorganize folders
Pull Request -
State: closed - Opened by markkho over 2 years ago
#68 - Clean up tests
Pull Request -
State: closed - Opened by markkho over 2 years ago
#67 - References
Issue -
State: open - Opened by markkho over 2 years ago
#66 - Refactoring Markov Policy Classes
Issue -
State: closed - Opened by markkho over 2 years ago
- 1 comment
#65 - Dynamic Programming Algorithm Refactoring
Pull Request -
State: closed - Opened by markkho over 2 years ago
#64 - add RMAX agent
Pull Request -
State: closed - Opened by zhouzypaul over 2 years ago
- 7 comments
#63 - RMAX?
Issue -
State: closed - Opened by zhouzypaul over 2 years ago
- 2 comments
#62 - fix q learning initial q values
Pull Request -
State: closed - Opened by zhouzypaul over 2 years ago
#61 - [BUG] Q values are not initialized correctly
Issue -
State: closed - Opened by zhouzypaul over 2 years ago
- 3 comments
#60 - Fix UniformDistribution duplicate elements, add default impl of FiniteDistribution.__len__
Pull Request -
State: closed - Opened by cgc almost 3 years ago
#59 - Uniform distribution
Issue -
State: closed - Opened by markkho almost 3 years ago
- 3 comments
#58 - PPL and syntatic sugar
Pull Request -
State: closed - Opened by markkho almost 3 years ago
#57 - Distributions
Pull Request -
State: closed - Opened by markkho almost 3 years ago
#56 - PI and VI inconsistent handling of reachability
Issue -
State: closed - Opened by markkho almost 3 years ago
- 3 comments
#55 - Distribution add ons
Issue -
State: open - Opened by markkho about 3 years ago
- 1 comment
#54 - Reachable non-terminal states
Issue -
State: closed - Opened by markkho about 3 years ago
- 1 comment
#53 - Softmax policy
Issue -
State: closed - Opened by markkho about 3 years ago
- 1 comment
#52 - Convert unittest.TestCase use to py.test conventions
Issue -
State: closed - Opened by cgc about 3 years ago
- 1 comment
#51 - Lrtdp refactor
Pull Request -
State: closed - Opened by markkho about 3 years ago
#50 - Laostar refactor
Pull Request -
State: closed - Opened by markkho about 3 years ago
#49 - First pass at CanonicalMDP
Pull Request -
State: closed - Opened by cgc over 3 years ago
#48 - Bounded Policy Iteration
Pull Request -
State: closed - Opened by cgc over 3 years ago
#47 - Stochastic FSC
Pull Request -
State: closed - Opened by cgc over 3 years ago
#46 - Tiger
Issue -
State: closed - Opened by markkho over 3 years ago
- 1 comment
#45 - POMDPs
Pull Request -
State: closed - Opened by markkho over 3 years ago
#44 - TabularMDP canonical representations
Issue -
State: open - Opened by markkho over 3 years ago
- 8 comments
#43 - v0.4 release
Pull Request -
State: closed - Opened by markkho over 3 years ago
#42 - Using juliapomdps and PyCall across python executables
Issue -
State: open - Opened by markkho over 3 years ago
- 1 comment
#41 - Fix juliapomdp
Pull Request -
State: closed - Opened by markkho over 3 years ago
#40 - Abstraction for monitoring algorithms
Issue -
State: closed - Opened by markkho over 3 years ago
- 2 comments
#39 - `from_matrices()` constructor for TabularMDP
Issue -
State: closed - Opened by markkho over 3 years ago
- 2 comments
#38 - Better document how absorbing vs terminal states work
Issue -
State: open - Opened by markkho over 3 years ago
Labels: documentation
#37 - Refactoring Tabular MDP code
Issue -
State: open - Opened by markkho over 3 years ago
- 1 comment
#36 - Add implementation of entropy-regularized policy iteration
Pull Request -
State: closed - Opened by markkho over 3 years ago
#35 - Optimize pickled representation through a custom __getstate__
Issue -
State: open - Opened by cgc over 3 years ago
- 3 comments
#34 - Extending dict in Python 3.9
Issue -
State: closed - Opened by markkho over 3 years ago
- 1 comment
#33 - Hardmax and floating point precision
Issue -
State: closed - Opened by markkho almost 4 years ago
- 1 comment
#32 - immutables
Issue -
State: closed - Opened by markkho almost 4 years ago
#31 - Distfeatures
Pull Request -
State: closed - Opened by markkho almost 4 years ago
#30 - Stochastic games refactor
Issue -
State: open - Opened by markkho almost 4 years ago
#29 - Entropy Regularization
Issue -
State: open - Opened by markkho almost 4 years ago
#28 - Add softmax distribution
Pull Request -
State: closed - Opened by markkho almost 4 years ago
- 1 comment
#27 - Use RNG in sampling, Add more types, Changes to QuickTMDP.
Pull Request -
State: closed - Opened by cgc almost 4 years ago
#26 - Wrapping up distributions
Pull Request -
State: closed - Opened by cgc almost 4 years ago
#25 - Tiny performance improvements
Pull Request -
State: closed - Opened by cgc almost 4 years ago
- 2 comments
#24 - Tabular mdp opt
Pull Request -
State: closed - Opened by markkho almost 4 years ago
#23 - Performance tweaks
Pull Request -
State: closed - Opened by cgc almost 4 years ago
- 1 comment
#22 - Hashable States/Actions
Issue -
State: closed - Opened by markkho almost 4 years ago
- 1 comment
#21 - Randomness
Issue -
State: closed - Opened by markkho almost 4 years ago
- 1 comment
#20 - Perf improvements
Pull Request -
State: closed - Opened by cgc almost 4 years ago
#19 - Various fixes following #11
Pull Request -
State: closed - Opened by cgc almost 4 years ago
#18 - Distribution refactor
Pull Request -
State: closed - Opened by markkho almost 4 years ago
#17 - Remove Dependency on AssignmentMap
Pull Request -
State: closed - Opened by markkho almost 4 years ago
#16 - DeterministicTabularPolicy
Issue -
State: closed - Opened by markkho almost 4 years ago
- 2 comments
#15 - Making it easier to ensure convergence
Issue -
State: closed - Opened by cgc almost 4 years ago
- 6 comments
#14 - Fixing RTDP solutions to trivial (solved) tasks.
Pull Request -
State: closed - Opened by cgc almost 4 years ago
#13 - Entropy regularized VI
Pull Request -
State: closed - Opened by cgc almost 4 years ago
#12 - Avoiding scipy softmax/logsumexp
Issue -
State: open - Opened by markkho almost 4 years ago
- 1 comment
#11 - Small tweaks, and performance improvement for uncached MDPs
Pull Request -
State: closed - Opened by cgc almost 4 years ago
#10 - Tabular stochastic game
Pull Request -
State: closed - Opened by markkho almost 4 years ago
#9 - Updated testing, etc. from master branch
Pull Request -
State: closed - Opened by markkho about 4 years ago
#8 - Fixing grid game collisions
Pull Request -
State: closed - Opened by markkho about 4 years ago
#7 - Merging in Daniel's tabular stochastic game branch
Pull Request -
State: closed - Opened by markkho about 4 years ago
#6 - POMDPs
Issue -
State: closed - Opened by cgc over 4 years ago
- 4 comments
#5 - Policy Representation
Issue -
State: closed - Opened by markkho over 4 years ago
- 2 comments
#4 - First pass at deterministic problem class, with BFS and A*.
Pull Request -
State: closed - Opened by cgc over 4 years ago
#3 - Partial Policies and changes to Assignment classes
Pull Request -
State: closed - Opened by markkho over 4 years ago
#2 - Adding in tabular stochastic game, tabular grid game and multiagent Q Learning
Pull Request -
State: closed - Opened by danieldritter over 4 years ago
- 1 comment
#1 - renaming to snakecase
Pull Request -
State: closed - Opened by markkho over 4 years ago