issues
search
markkho
/
msdm
Models of Sequential Decision-Making
MIT License
44
stars
6
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Fix issue where A* ignored subsequent visits to states that could have improved plans.
#79
cgc
closed
1 year ago
0
A*: Throw error when heuristic is not admissible
#78
cgc
closed
11 months ago
3
Bidirectional search
#77
Reeche
closed
1 year ago
0
Fix tie-breaking
#76
markkho
closed
1 year ago
0
A* clean up
#75
markkho
closed
1 year ago
0
A* LIFO/FIFO options
#74
markkho
closed
1 year ago
1
Astar refactor
#73
markkho
closed
1 year ago
0
Implicit Distribution
#72
markkho
closed
1 year ago
0
Cython implementations of tabular MDPs and algorithms
#71
markkho
opened
1 year ago
0
Options framework
#70
markkho
closed
1 year ago
0
Reorganize folders
#69
markkho
closed
1 year ago
0
Clean up tests
#68
markkho
closed
2 years ago
0
References
#67
markkho
opened
2 years ago
0
Refactoring Markov Policy Classes
#66
markkho
closed
2 years ago
1
Dynamic Programming Algorithm Refactoring
#65
markkho
closed
2 years ago
0
add RMAX agent
#64
zhouzypaul
closed
2 years ago
7
RMAX?
#63
zhouzypaul
closed
2 years ago
2
fix q learning initial q values
#62
zhouzypaul
closed
2 years ago
0
[BUG] Q values are not initialized correctly
#61
zhouzypaul
closed
2 years ago
3
Fix UniformDistribution duplicate elements, add default impl of FiniteDistribution.__len__
#60
cgc
closed
2 years ago
0
Uniform distribution
#59
markkho
closed
2 years ago
3
PPL and syntatic sugar
#58
markkho
closed
1 year ago
0
Distributions
#57
markkho
closed
2 years ago
0
PI and VI inconsistent handling of reachability
#56
markkho
closed
2 years ago
3
Distribution add ons
#55
markkho
opened
2 years ago
1
Reachable non-terminal states
#54
markkho
closed
2 years ago
1
Softmax policy
#53
markkho
closed
2 years ago
1
Convert unittest.TestCase use to py.test conventions
#52
cgc
closed
2 years ago
1
Lrtdp refactor
#51
markkho
closed
2 years ago
0
Laostar refactor
#50
markkho
closed
2 years ago
0
First pass at CanonicalMDP
#49
cgc
closed
2 years ago
0
Bounded Policy Iteration
#48
cgc
closed
2 years ago
0
Stochastic FSC
#47
cgc
closed
3 years ago
0
Tiger
#46
markkho
closed
3 years ago
1
POMDPs
#45
markkho
closed
3 years ago
0
TabularMDP canonical representations
#44
markkho
opened
3 years ago
8
v0.4 release
#43
markkho
closed
3 years ago
0
Using juliapomdps and PyCall across python executables
#42
markkho
opened
3 years ago
1
Fix juliapomdp
#41
markkho
closed
3 years ago
0
Abstraction for monitoring algorithms
#40
markkho
closed
3 years ago
2
`from_matrices()` constructor for TabularMDP
#39
markkho
closed
3 years ago
2
Better document how absorbing vs terminal states work
#38
markkho
opened
3 years ago
0
Refactoring Tabular MDP code
#37
markkho
opened
3 years ago
1
Add implementation of entropy-regularized policy iteration
#36
markkho
closed
3 years ago
0
Optimize pickled representation through a custom __getstate__
#35
cgc
opened
3 years ago
3
Extending dict in Python 3.9
#34
markkho
closed
3 years ago
1
Hardmax and floating point precision
#33
markkho
closed
3 years ago
1
immutables
#32
markkho
closed
2 years ago
0
Distfeatures
#31
markkho
closed
3 years ago
0
Stochastic games refactor
#30
markkho
opened
3 years ago
0
Next