GitHub - adelegi/Approximate_DMDP: Implementation of algorithms solving approximate policy in Discounted Markov Decision Processes (DMDP). Some of those algorithms are from "Variance Reduced Value Iteration and Faster Algorithms for Solving Markov Decision Processes" of Aaron Sidford, Mengdi Wang, Xian Wu, Yinyu Ye https://arxiv.org/pdf/1710.09988.pdf

adelegi / Approximate_DMDP Public

Notifications You must be signed in to change notification settings
Fork 1
Star 2

Implementation of algorithms solving approximate policy in Discounted Markov Decision Processes (DMDP). Some of those algorithms are from "Variance Reduced Value Iteration and Faster Algorithms for Solving Markov Decision Processes" of Aaron Sidford, Mengdi Wang, Xian Wu, Yinyu Ye https://arxiv.org/pdf/1710.09988.pdf

2 stars 1 fork Branches Tags Activity

Star

Notifications

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 15 Commits
Examples		Examples
.gitignore		.gitignore
DMDP_class.py		DMDP_class.py
high_precision_randomized_VI.py		high_precision_randomized_VI.py
linear_programming.py		linear_programming.py
monotonic_randomized_VI.py		monotonic_randomized_VI.py
randomized_primal_dual.py		randomized_primal_dual.py
randomized_value_iteration.py		randomized_value_iteration.py
run_test.py		run_test.py
sampling_tree.py		sampling_tree.py
sublinear_radomizedVI.py		sublinear_radomizedVI.py
tools.py		tools.py
value_iteration.py		value_iteration.py