Difference between revisions of "Actor Critic"
m (Text replacement - "http:" to "https:") |
m |
||
| Line 22: | Line 22: | ||
*** [[Lifelong Latent Actor-Critic (LILAC)]] | *** [[Lifelong Latent Actor-Critic (LILAC)]] | ||
** [[Hierarchical Reinforcement Learning (HRL)]] | ** [[Hierarchical Reinforcement Learning (HRL)]] | ||
| − | |||
| − | |||
* [https://towardsdatascience.com/advanced-reinforcement-learning-6d769f529eb3 Beyond DQN/A3C: A Survey in Advanced Reinforcement Learning | Joyce Xu - Towards Data Science] | * [https://towardsdatascience.com/advanced-reinforcement-learning-6d769f529eb3 Beyond DQN/A3C: A Survey in Advanced Reinforcement Learning | Joyce Xu - Towards Data Science] | ||
| − | * [[Policy Gradient (PG)]] | + | * [[Policy]] ... [[Policy vs Plan]] ... [[Constitutional AI]] ... [[Trust Region Policy Optimization (TRPO)]] ... [[Policy Gradient (PG)]] ... [[Proximal Policy Optimization (PPO)]] |
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. | 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. | ||
| Line 31: | Line 29: | ||
<youtube>2vJtbAha3To</youtube> | <youtube>2vJtbAha3To</youtube> | ||
<youtube>CLZkpo8rEG</youtube> | <youtube>CLZkpo8rEG</youtube> | ||
| − | |||
<youtube>aODdNpihRwM</youtube> | <youtube>aODdNpihRwM</youtube> | ||
<youtube>w_3mmm0P0j8</youtube> | <youtube>w_3mmm0P0j8</youtube> | ||
Revision as of 15:38, 16 April 2023
YouTube search... ...Google search
- Reinforcement Learning (RL)
- Monte Carlo (MC) Method - Model Free Reinforcement Learning
- Markov Decision Process (MDP)
- State-Action-Reward-State-Action (SARSA)
- Q Learning
- Deep Reinforcement Learning (DRL) DeepRL
- Distributed Deep Reinforcement Learning (DDRL)
- Evolutionary Computation / Genetic Algorithms
- Actor Critic
- Hierarchical Reinforcement Learning (HRL)
- Beyond DQN/A3C: A Survey in Advanced Reinforcement Learning | Joyce Xu - Towards Data Science
- Policy ... Policy vs Plan ... Constitutional AI ... Trust Region Policy Optimization (TRPO) ... Policy Gradient (PG) ... Proximal Policy Optimization (PPO)
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.
