Riashat/Q-Learning-SARSA-Policy-and-Value-Iteration Riashat/Q-Learning-SARSA-Policy-and-Value-Iteration

  • Stars
    star
    36
  • Rank 735,472 (Top 15 %)
  • Language
    MATLAB
  • Created almost 9 years ago
  • Updated almost 9 years ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
Riashat/Q-Learning-SARSA-Policy-and-Value-Iteration
github

Riashat

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Implementation of basic reinforcement learning algorithms (Q-learning, SARSA, Policy iteration and Value Iteration) on benchmark RL MDPs (GridWorld, SmallWorld and CliffWorld)

More Repositories

1

Active-Learning-Bayesian-Convolutional-Neural-Networks

Active Learning on Image Data using Bayesian ConvNets
Python
135
star
2

Deep-Bayesian-Active-Learning

Code for Deep Bayesian Active Learning (ICML 2017)
Python
111
star
3

Policy-Gradient-Reinforcement-Learning

MATLAB
33
star
4

Bayesian-Exploration-Deep-RL

Bayesian Uncertainty Exploration in Deep Reinforcement Learning
Python
17
star
5

Temporal_Difference_Learning

Code for TD Learning algorithms in Reinforcement Learning
Python
5
star
6

Dropout-Uncertainty-Exploration-DQN

Exploration Exploitation in DQNs using Dropout as Bayesian Approximation
Python
5
star
7

meta-active-learning

Meta-Learning Bayesian Active Learning Algorithms
Python
5
star
8

Model-Free-Control-Reinforcement-Learning

MATLAB
4
star
9

Multi-Step-Bootstrapping

Q(sigma), Expected SARSA and n-step Tree Backup Algorithms
Python
3
star
10

Q_Sigma_Tree_Backup_Eligibility_Traces

Python
3
star
11

Credit_Assignment_RL

Credit Assignment in Reinforcement Learning
Python
1
star
12

Trust_DDPG

Trust Region constrained updates for DDPG
Python
1
star
13

Plotting_Scripts

Sample Plotting Script to use
Python
1
star
14

Soft_Trust_Region_A2C

Soft Trust Region Constraints on A2C
HTML
1
star