Difference between revisions of "Actor Critic"
| Line 18: | Line 18: | ||
** [[Evolutionary Computation / Genetic Algorithms]] | ** [[Evolutionary Computation / Genetic Algorithms]] | ||
** [[Hierarchical Reinforcement Learning (HRL)]] | ** [[Hierarchical Reinforcement Learning (HRL)]] | ||
| − | |||
* [http://towardsdatascience.com/advanced-reinforcement-learning-6d769f529eb3 Beyond DQN/A3C: A Survey in Advanced Reinforcement Learning | Joyce Xu - Towards Data Science] | * [http://towardsdatascience.com/advanced-reinforcement-learning-6d769f529eb3 Beyond DQN/A3C: A Survey in Advanced Reinforcement Learning | Joyce Xu - Towards Data Science] | ||
* [[Policy Gradient (PG)]] | * [[Policy Gradient (PG)]] | ||
Revision as of 20:16, 1 September 2019
YouTube search... ...Google search
- Reinforcement Learning (RL):
- Monte Carlo (MC) Method - Model Free Reinforcement Learning
- Markov Decision Process (MDP)
- Q Learning
- State-Action-Reward-State-Action (SARSA)
- Deep Reinforcement Learning (DRL) DeepRL
- Distributed Deep Reinforcement Learning (DDRL)
- Deep Q Network (DQN)
- Evolutionary Computation / Genetic Algorithms
- Hierarchical Reinforcement Learning (HRL)
- Beyond DQN/A3C: A Survey in Advanced Reinforcement Learning | Joyce Xu - Towards Data Science
- Policy Gradient (PG)
Policy gradients and Deep Q Network (DQN) can only get us so far, but what if we used two networks to help train and AI instead of one? Thats the idea behind actor critic algorithms.
Asynchronous Advantage Actor Critic (A3C)
