Difference between revisions of "Advanced Actor Critic (A2C)"
| Line 24: | Line 24: | ||
* [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)]] | ||
| + | * [[Proximal Policy Optimization (PPO)]] | ||
A2C produces comparable performance to [[Asynchronous Advantage Actor Critic (A3C)]] while being more efficient. A2C is like A3C but without the asynchronous part; this means a single-worker variant of the A3C. [http://towardsdatascience.com/understanding-actor-critic-methods-931b97b6df3f Understanding Actor Critic Methods and A2C | Chris Yoon - Towards Data Science] | A2C produces comparable performance to [[Asynchronous Advantage Actor Critic (A3C)]] while being more efficient. A2C is like A3C but without the asynchronous part; this means a single-worker variant of the A3C. [http://towardsdatascience.com/understanding-actor-critic-methods-931b97b6df3f Understanding Actor Critic Methods and A2C | Chris Yoon - Towards Data Science] | ||
Revision as of 15:20, 3 July 2020
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
- Actor Critic
- Advanced Actor Critic (A2C)
- Asynchronous Advantage Actor Critic (A3C)
- Lifelong Latent Actor-Critic (LILAC)
- Hierarchical Reinforcement Learning (HRL)
- Beyond DQN/A3C: A Survey in Advanced Reinforcement Learning | Joyce Xu - Towards Data Science
- Policy Gradient (PG)
- Proximal Policy Optimization (PPO)
A2C produces comparable performance to Asynchronous Advantage Actor Critic (A3C) while being more efficient. A2C is like A3C but without the asynchronous part; this means a single-worker variant of the A3C. Understanding Actor Critic Methods and A2C | Chris Yoon - Towards Data Science
