Series of Reinforcement Learning: Q-Learning, Sarsa, SarsaLambda, Deep Q Learning(DQN);一些列强化学习算法,玩OpenAI-gym游戏
-
Updated
Jul 8, 2017 - Python
Series of Reinforcement Learning: Q-Learning, Sarsa, SarsaLambda, Deep Q Learning(DQN);一些列强化学习算法,玩OpenAI-gym游戏
Reinforcement learning in Julia. Solving OpenAI gym.
Implement dynamic programming to solve an AI frozen lake problem.
Resolving the FrozenLake problem from OpenAI Gym.
An implementation of main reinforcement learning algorithms: solo-agent and ensembled versions.
Implementation of DQN using just Numpy (SFC project)
EATED 2018 DQN을 이용한 고전게임 강화학습
Algorithms for Policy Evaluation, Estimation of Action Values, Policy Improvement, Policy Iteration, Truncated Policy Evaluation, Truncated Policy Iteration, Value Iteration . From Udacity's Deep Reinforcement Learning Nanodegree program.
Bots for Atari Games using Reinforcement Learning
FrozenLake - OpenAI's exercise resolved with Q-learning algorithm
Reinforcing Your Learning of Reinforcement Learning
Contains the implementation of SARSA, Q-learning and E-SARSA on gym environment.
The task contains three different agents. A random agent, a simple agent and a RL agent. The problem is similar to the Frozen Lake problem which introduced by Open AI Gym. It requires the agent to “learn” how to get across the lake from the start point to the goal point and not to fall into a hole.
Reinforcement learning algorithms to solve OpenAI gym environments
The module covers different Q learning algorithms using Open AI and FrozenLake.
Implementation of certain crucial algorithms in the field of reinforcement learning.
Uses Q learning to give instructions to a skater on slippery ice(stochastic model) to reach his goal.
Add a description, image, and links to the frozenlake topic page so that developers can more easily learn about it.
To associate your repository with the frozenlake topic, visit your repo's landing page and select "manage topics."