-
Monte Carlo Prediction method reinforcement learning agent for BlackJack Game.
-
Temporal Difference methods like
- SARSA(0)
- SARSAMAX(Q-Learning)
- Expected SARSA
- and some experiments with TD Methods
-
Approximation of state-action value function(Q function) with Deep Neural networks.
- Deep Q Network
- Double Deep Q network
- Dueling Deep Q Network
-
Policy function aproximation with Deep NNs.
- Optimization methods like Hill Climbing, Cross Entropy.
- Gradient Based methods
- Policy Gradient
- Proximal Policy Approximation
Last active
November 8, 2019 19:29
-
-
Save shangeth/f0ca6edfe1ba0cbbcce76919e445aaec to your computer and use it in GitHub Desktop.
List of projects worked on by shangeth(shangeth.com) on Deep Reinforcement Learning
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment