Implementation of various reinforcement learning algorithms in examples obtained from the book "Reinforcement Learning: An Introduction, by Sutton and Barto".
-
Updated
Feb 7, 2022 - MATLAB
#
cliff-walking-problem
Here are 7 public repositories matching this topic...
This repo implements Deep Q-Network (DQN) for solving the Cliff Walking v0 environment of the Gymnasium library using Python 3.8 and PyTorch 2.0.1 with the finest tuning.
python reinforcement-learning deep-learning deep-reinforcement-learning q-learning pytorch dqn gym deep-q-network gymnasium drl deep-q-learning cliffwalking drl-pytorch cliff-walking-problem
-
Updated
Mar 19, 2024 - Python
Four reinforcement learning algorithms — Value Iteration, Direct Estimation, Q-Learning and REINFORCE — implemented, swept and compared on the Cliff Walking environment, with the learned policies visualized
python machine-learning reinforcement-learning qlearning reinforce value-iteration gymnasium markov-decision-process cliff-walking-problem
-
Updated
Jun 28, 2026 - Python
Comparing SARSA, Q-Learning, and Double Q-Learning on Cliff Walking and Taxi-V3 Tasks
reinforcement-learning qlearning sarsa temporal-differencing-learning double-q-learning taxi-v3 cliff-walking-problem
-
Updated
Jun 24, 2026 - Jupyter Notebook
Implementation of Q-learning and SARSA algorithms in the Cliff Walking environment. Explore and compare reinforcement learning techniques.
-
Updated
Aug 25, 2024 - Jupyter Notebook
Q-Learning agent that learns to navigate a 4×12 cliff-edge grid using ε-greedy exploration and Bellman updates — trained from scratch with NumPy + Gymnasium in 63 lines of Python.
python reinforcement-learning numpy openai-gym q-learning epsilon-greedy gymnasium bellman-equation temporal-difference model-free-rl tabular-rl cliff-walking-problem
-
Updated
Jun 5, 2026 - Python
🧗Comparative Reinforcement Learning analysis implementing SARSA (On-Policy) vs Q-Learning (Off-Policy) from scratch on OpenAI Gymnasium CliffWalking-v1 with live side-by-side animations and policy heatmaps.
python machine-learning reinforcement-learning numpy jupyter-notebook openai-gym q-learning python3 seaborn artificial-intelligence grid-world sarsa matplotlib markov-decision-processes gymnasium td-learning on-policy off-policy temporal-difference cliff-walking-problem
-
Updated
Jul 28, 2026 - Jupyter Notebook
Improve this page
Add a description, image, and links to the cliff-walking-problem topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the cliff-walking-problem topic, visit your repo's landing page and select "manage topics."