An a bias-variance tradeoff of Sarsa vs. Expected Sarsa with experiments.
-
Updated
Feb 10, 2017 - Jupyter Notebook
An a bias-variance tradeoff of Sarsa vs. Expected Sarsa with experiments.
Exercise and assignments of Deep Reinforcement Learning Nanodegree Program offered by Udacity
SARSA, Q-Learning, Expected SARSA, SARSA(λ) and Double Q-learning Implementation and Analysis
Various fundamental reinforcement learning algorithms implemented from scratch
Autonomous Navigation of MAVs using Reinforcement Learning algorithms
This repository has RL algorithms implemented using python
A reinforcement learning framework for the game of Nim.
Using deep expected sarsa with tensorflow to solve the lunar lander problem with hyperparameter tuning and results analysis
An Expected SARSA RL agent created to solve the Mountain Car problem.
AI Agent that learns to play Snake with Reinforcement Learning using a Deep Q-Network (SARSA, Q-Learning and Expected SARSA)
Implementation of TD Learning algorithms for Drone Parrot for TCS Project
Solving Markov Decision Process using Value Iteration and Policy Iteration, SARSA, Expected SARSA and Q-Learning
This repo contains python implementation to the cliff walking problem from RL Introduction by Sutton & Barto Example 6.6.
Implementation of Q-Learning and Expected SARSA algorithms to solve the Text-Flappy-Bird game
Compare q-learning, SARSA and Expected SARSA to solve AI gym's Taxi-v3 environment
Reversi game with multiple reinforcement learning algorithms.
Some of my solutions of the exercises and all my projects of the Udacity Deep Reinforcement Learning Nanodegree https://www.udacity.com/course/deep-reinforcement-learning-nanodegree--nd893
Reinforcement Learning (COMP 579) Project
Advanced RL algorithms for two simplified versions of chess. Shortest Path finds the minimal moves between two cells based on piece capabilities. Capture Pieces trains against random opponents aiming for maximal captures in set moves. Features Deep Q-Learning, Policy Iteration, TD and more.
First task for my Reinforcement Learning class in Deusto. The research paper the main RL algorithms applied on the Frozen Lake env provided by GymOpenAI. Paper is avaible at:
Add a description, image, and links to the expected-sarsa topic page so that developers can more easily learn about it.
To associate your repository with the expected-sarsa topic, visit your repo's landing page and select "manage topics."