Solving the Gambler's Problem using Value Iteration from the book Reinforcement Learning (2nd Edition) by Richard S. Sutton and Andre G. Barto
-
Updated
Nov 29, 2019 - Python
#
gambler-problem
Here are 7 public repositories matching this topic...
A simulation of the gambler's ruin problem: the traditional set-up with 2 players, as well as a general solution in n players.
-
Updated
Aug 30, 2020 - Python
python code successfullly reproduce the Gambler problem, Figure 4.6 of Chapter 4 on Sutton's book, Sutton, R. S., & Barto, A. G. (1998). Reinforcement learning: An introduction (Vol. 1, No. 1). Cambridge: MIT press.
-
Updated
Dec 19, 2017 - Python
A dynamic programming solution to the classic gambler's problem introduced in Sutton and Barton's RL book
-
Updated
Apr 7, 2019 - Python
Gambler's problem environment implemented OpenAI gym-style
-
Updated
Jan 4, 2019 - Python
multi-armed bandit, gambler problem, cliff problem and TD learning
-
Updated
Jun 2, 2021 - Python
Two Markov Decision Process (MDP) problems – the Frozen Lake and the Gambler’s Problem MDPs. Policy iteration, value iteration and the Q-Learning reinforcement learning algorithm are implemented on each of the MDPs and are analyzed.
machine-learning reinforcement-learning jupyter-notebook openai-gym q-learning dynamic-programming markov-decision-processes policy-iteration value-iteration gymnasium georgia-tech gambler-problem cs7641 frozen-lake bettermdptools
-
Updated
Sep 28, 2026 - Jupyter Notebook
Add this topic to your repo
To associate your repository with the gambler-problem topic, visit your repo's landing page and select "manage topics."