Difference between revisions of "Distributed Deep Reinforcement Learning (DDRL)"
| Line 8: | Line 8: | ||
[http://www.google.com/search?q=Distributed+Deep+Reinforcement+Learning+DeepRL+machine+learning+ML+artificial+intelligence ...Google search] | [http://www.google.com/search?q=Distributed+Deep+Reinforcement+Learning+DeepRL+machine+learning+ML+artificial+intelligence ...Google search] | ||
| − | |||
* [http://deepmind.com/blog/impala-scalable-distributed-deeprl-dmlab-30/ Importance Weighted Actor-Learner Architectures: Scalable Distributed DeepRL in DMLab-30] | * [http://deepmind.com/blog/impala-scalable-distributed-deeprl-dmlab-30/ Importance Weighted Actor-Learner Architectures: Scalable Distributed DeepRL in DMLab-30] | ||
* Reinforcement Learning (RL): | * Reinforcement Learning (RL): | ||
Revision as of 20:01, 1 September 2019
Youtube search... ...Google search
- Importance Weighted Actor-Learner Architectures: Scalable Distributed DeepRL in DMLab-30
- 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
- Deep Q Network (DQN)
- Evolutionary Computation / Genetic Algorithms
- Actor Critic
- Hierarchical Reinforcement Learning (HRL)
a new, highly scalable agent architecture for distributed training called Importance Weighted Actor-Learner Architecture that uses a new off-policy correction algorithm called V-trace.
