Here, we compare Q(\sigma) learning presented by Sutton and Barto in [1] to Tree-Backup, n-step Expected Sarsa, and n-step Sarsa.
-
Updated
Feb 17, 2017 - Python
#
tree-backup
Here are 3 public repositories matching this topic...
Interactive Learning Course | Home Works & Quiz | Fall 2021 | Prof. Majid Nili
q-learning
epsilon-greedy
sarsa
value-iteration
tree-backup
n-armed-bandit-problem
regret-minimization
multi-agent-multi-armed-bandits
2-step-tree-backup
model-based-learning
off-policy-monte-carlo
social-bandit-learning
reinforcement-comparison
model-based-model-free-mixture
-
Updated
Feb 24, 2022 - Jupyter Notebook
Containing a custom-built Reinforcement Learning environment and implementations of key RL algorithms like Q-learning and SARSA, tested in scenarios such as a drone navigation challenge and the Frozen Lake environment.
q-learning
mdp
grid-world
sarsa
markov-decision-processes
value-iteration
tree-backup
on-policy
off-policy
-
Updated
Aug 9, 2024 - Jupyter Notebook
Improve this page
Add a description, image, and links to the tree-backup topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the tree-backup topic, visit your repo's landing page and select "manage topics."