Issues
- 3
- 1
A* LIFO/FIFO options
#74 opened - 0
References
#67 opened - 1
Refactoring Markov Policy Classes
#66 opened - 2
RMAX?
#63 opened - 3
[BUG] Q values are not initialized correctly
#61 opened - 3
Uniform distribution
#59 opened - 3
- 1
Distribution add ons
#55 opened - 1
Reachable non-terminal states
#54 opened - 1
Softmax policy
#53 opened - 1
- 1
Tiger
#46 opened - 8
TabularMDP canonical representations
#44 opened - 1
- 2
Abstraction for monitoring algorithms
#40 opened - 2
- 0
- 1
Refactoring Tabular MDP code
#37 opened - 3
- 1
Extending dict in Python 3.9
#34 opened - 1
Hardmax and floating point precision
#33 opened - 0
immutables
#32 opened - 0
Stochastic games refactor
#30 opened - 0
Entropy Regularization
#29 opened - 1
Hashable States/Actions
#22 opened - 1
Randomness
#21 opened - 2
DeterministicTabularPolicy
#16 opened - 6
Making it easier to ensure convergence
#15 opened - 1
Avoiding scipy softmax/logsumexp
#12 opened - 4
POMDPs
#6 opened - 2
Policy Representation
#5 opened