Difference between revisions of "Deep Reinforcement Learning (DRL)"
| Line 1: | Line 1: | ||
[http://www.youtube.com/results?search_query=deep+reinforcement+learning+ Youtube search...] | [http://www.youtube.com/results?search_query=deep+reinforcement+learning+ Youtube search...] | ||
| − | === OTHER: Learning; MDP, Q, and SARSA === | + | ==== OTHER: Learning; MDP, Q, and SARSA ==== |
* [[Markov Decision Process (MDP)]] | * [[Markov Decision Process (MDP)]] | ||
* [[Deep Q Learning (DQN)]] | * [[Deep Q Learning (DQN)]] | ||
| Line 7: | Line 7: | ||
* [[State-Action-Reward-State-Action (SARSA)]] | * [[State-Action-Reward-State-Action (SARSA)]] | ||
| − | === OTHER: Policy Gradient Methods === | + | ==== OTHER: Policy Gradient Methods ==== |
* [[Deep Deterministic Policy Gradient (DDPG)]] | * [[Deep Deterministic Policy Gradient (DDPG)]] | ||
* [[Trust Region Policy Optimization (TRPO)]] | * [[Trust Region Policy Optimization (TRPO)]] | ||
* [[Proximal Policy Optimization (PPO)]] | * [[Proximal Policy Optimization (PPO)]] | ||
| − | + | _______________________________________________________________________________________ | |
* [http://gym.openai.com/ Gym | OpenAI] | * [http://gym.openai.com/ Gym | OpenAI] | ||
Revision as of 06:29, 27 May 2018
OTHER: Learning; MDP, Q, and SARSA
- Markov Decision Process (MDP)
- Deep Q Learning (DQN)
- Neural Coreference
- State-Action-Reward-State-Action (SARSA)
OTHER: Policy Gradient Methods
- Deep Deterministic Policy Gradient (DDPG)
- Trust Region Policy Optimization (TRPO)
- Proximal Policy Optimization (PPO)
_______________________________________________________________________________________
- Gym | OpenAI
- Introduction to Various Reinforcement Learning Algorithms. Part I (Q-Learning, SARSA, DQN, DDPG) | Steeve Huang
- Introduction to Various Reinforcement Learning Algorithms. Part II (TRPO, PPO) | Steeve Huang
- Guide
Goal-oriented algorithms, which learn how to attain a complex objective (goal) or maximize along a particular dimension over many steps; for example, maximize the points won in a game over many moves. Reinforcement learning solves the difficult problem of correlating immediate actions with the delayed returns they produce. Like humans, reinforcement learning algorithms sometimes have to wait a while to see the fruit of their decisions. They operate in a delayed return environment, where it can be difficult to understand which action leads to which outcome over many time steps.
