Difference between revisions of "Deep Reinforcement Learning (DRL)"
m |
m (Text replacement - "http:" to "https:") |
||
| Line 5: | Line 5: | ||
|description=Helpful resources for your journey with artificial intelligence; videos, articles, techniques, courses, profiles, and tools | |description=Helpful resources for your journey with artificial intelligence; videos, articles, techniques, courses, profiles, and tools | ||
}} | }} | ||
| − | [ | + | [https://www.youtube.com/results?search_query=deep+reinforcement+learning Youtube search...] |
| − | [ | + | [https://www.google.com/search?q=reinforcement+machine+learning+ML+artificial+intelligence ...Google search] |
* [[Reinforcement Learning (RL)]] | * [[Reinforcement Learning (RL)]] | ||
| Line 35: | Line 35: | ||
* [https://towardsdatascience.com/introduction-to-various-reinforcement-learning-algorithms-i-q-learning-sarsa-dqn-ddpg-72a5e0cb6287 Introduction to Various Reinforcement Learning Algorithms. Part I (Q-Learning, SARSA, DQN, DDPG) | Steeve Huang] | * [https://towardsdatascience.com/introduction-to-various-reinforcement-learning-algorithms-i-q-learning-sarsa-dqn-ddpg-72a5e0cb6287 Introduction to Various Reinforcement Learning Algorithms. Part I (Q-Learning, SARSA, DQN, DDPG) | Steeve Huang] | ||
* [https://towardsdatascience.com/introduction-to-various-reinforcement-learning-algorithms-part-ii-trpo-ppo-87f2c5919bb9 Introduction to Various Reinforcement Learning Algorithms. Part II (TRPO, PPO) | Steeve Huang] | * [https://towardsdatascience.com/introduction-to-various-reinforcement-learning-algorithms-part-ii-trpo-ppo-87f2c5919bb9 Introduction to Various Reinforcement Learning Algorithms. Part II (TRPO, PPO) | Steeve Huang] | ||
| − | * [ | + | * [https://deeplearning4j.org/deepreinforcementlearning.html Guide] |
https://upload.wikimedia.org/wikipedia/commons/thumb/1/1b/Reinforcement_learning_diagram.svg/375px-Reinforcement_learning_diagram.svg.png | https://upload.wikimedia.org/wikipedia/commons/thumb/1/1b/Reinforcement_learning_diagram.svg/375px-Reinforcement_learning_diagram.svg.png | ||
| Line 50: | Line 50: | ||
== Importance Weighted Actor-Learner Architecture (IMPALA) == | == Importance Weighted Actor-Learner Architecture (IMPALA) == | ||
| − | [ | + | [https://www.youtube.com/results?search_query=Impala+AGI+machine+artificial+intelligence+deep+learning+simple YouTube search...] |
| − | [ | + | [https://www.google.com/search?q=Impala+AGIb+deep+machine+learning+ML ...Google search] |
| − | * [ | + | * [https://www.extremetech.com/extreme/275768-artificial-general-intelligence-is-here-and-impala-is-its-nameDeepMind Artificial General Intelligence Is Here, and Impala Is Its Name | Aaron Krumins] |
| − | * [ | + | * [https://deepmind.com/blog/open-sourcing-deepmind-lab/ DeepMind Lab] |
| − | * [ | + | * [https://deepmind.com/research/publications/impala-scalable-distributed-deep-rl-importance-weighted-actor-learner-architectures/ IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures] |
| − | * [ | + | * [https://deepmind.com/blog/impala-scalable-distributed-deeprl-dmlab-30/ Importance Weighted Actor-Learner Architectures: Scalable Distributed DeepRL in DMLab-30] |
uses resources more efficiently in single-machine training but also scales to thousands of machines without sacrificing data efficiency or resource utilisation. We achieve stable learning at high throughput by combining decoupled acting and learning with a novel off-policy correction method called V-trace. IMPALA is able to achieve better performance than previous [[agents]] with less data, and crucially exhibits positive transfer between tasks as a result of its multi-task approach. | uses resources more efficiently in single-machine training but also scales to thousands of machines without sacrificing data efficiency or resource utilisation. We achieve stable learning at high throughput by combining decoupled acting and learning with a novel off-policy correction method called V-trace. IMPALA is able to achieve better performance than previous [[agents]] with less data, and crucially exhibits positive transfer between tasks as a result of its multi-task approach. | ||
| − | + | https://ai2-s2-public.s3.amazonaws.com/figures/2017-08-08/cbddc41e5b07ad8e3f7982e232bafba84c8419cc/5-Figure3-1.png | |
| Line 68: | Line 68: | ||
== DMLab-30 == | == DMLab-30 == | ||
| − | [ | + | [https://www.youtube.com/results?search_query=DMLab-30+Distributed+Deep+Reinforcement+Learning+DeepRL Youtube search...] |
| − | [ | + | [https://www.google.com/search?q=Distributed+DMLab-30+Deep+Reinforcement+Learning+DeepRL+machine+learning+ML+artificial+intelligence ...Google search] |
DMLab-30 is a collection of new levels designed using our open source RL environment DeepMind Lab. These environments enable any DeepRL researcher to test systems on a large spectrum of interesting tasks either individually or in a multi-task setting. | DMLab-30 is a collection of new levels designed using our open source RL environment DeepMind Lab. These environments enable any DeepRL researcher to test systems on a large spectrum of interesting tasks either individually or in a multi-task setting. | ||
| − | * [ | + | * [https://github.com/deepmind/lab/tree/master/game_scripts/levels/contributed/dmlab30 DMLab-30 | GitHub] |
| − | * [ | + | * [https://www.techleer.com/articles/488-impala-distributed-agent-in-dmlab-30/ IMPALA distributed] [[Agents|agent]] in DMLab-30 |
| − | * [ | + | * [https://www.semanticscholar.org/paper/IMPALA%3A-Scalable-Distributed-Deep-RL-with-Weighted-Espeholt-Soyer/cbddc41e5b07ad8e3f7982e232bafba84c8419cc IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures] |
| − | + | https://s3.ap-south-1.amazonaws.com/techleerimages/4d62b60c-4dcd-4774-9c75-417eba1cbbc1.png | |
Revision as of 08:09, 28 March 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)
- MERLIN: Inside Out - Curious Optimistic Reasoning
- OpenAI Gym
OTHER: Policy Gradient Methods
_______________________________________________________________________________________
- 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.
Importance Weighted Actor-Learner Architecture (IMPALA)
YouTube search... ...Google search
- Artificial General Intelligence Is Here, and Impala Is Its Name | Aaron Krumins
- DeepMind Lab
- IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
- Importance Weighted Actor-Learner Architectures: Scalable Distributed DeepRL in DMLab-30
uses resources more efficiently in single-machine training but also scales to thousands of machines without sacrificing data efficiency or resource utilisation. We achieve stable learning at high throughput by combining decoupled acting and learning with a novel off-policy correction method called V-trace. IMPALA is able to achieve better performance than previous agents with less data, and crucially exhibits positive transfer between tasks as a result of its multi-task approach.
DMLab-30
Youtube search... ...Google search
DMLab-30 is a collection of new levels designed using our open source RL environment DeepMind Lab. These environments enable any DeepRL researcher to test systems on a large spectrum of interesting tasks either individually or in a multi-task setting.
- DMLab-30 | GitHub
- IMPALA distributed agent in DMLab-30
- IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
