Lifelong Latent Actor-Critic (LILAC) - Revision history

BPeat at 16:08, 16 September 2023

2023-09-16T16:08:35Z

BPeat at 16:05, 16 September 2023

2023-09-16T16:05:20Z

BPeat at 20:40, 16 April 2023

2023-04-16T20:40:33Z

BPeat: Text replacement - "http:" to "https:"

2023-03-29T02:55:10Z

Text replacement - "http:" to "https:"

BPeat at 11:16, 6 July 2020

2020-07-06T11:16:05Z

BPeat at 20:00, 3 July 2020

2020-07-03T20:00:52Z

BPeat at 19:55, 3 July 2020

2020-07-03T19:55:42Z

BPeat at 19:52, 3 July 2020

2020-07-03T19:52:24Z

BPeat at 19:30, 3 July 2020

2020-07-03T19:30:33Z

BPeat at 16:24, 3 July 2020

2020-07-03T16:24:00Z

@@ Line 26: / Line 26: @@
-Lifelong Latent Actor-Critic (LILAC) is an off-policy reinforcement learning algorithm that can reason about and tackle lifelong non-stationarity. It leverages latent variable models to learn a representation of the environment from current and past experiences, and performs off-policy [[Reinforcement Learning (RL)]] with this representation. LILAC is based on the following three key ideas:
+Lifelong Latent Actor-Critic (LILAC) is an off-policy reinforcement learning algorithm that can reason about and tackle lifelong non-stationarity. It leverages [[latent]] variable models to learn a representation of the environment from current and past experiences, and performs off-[[policy]] [[Reinforcement Learning (RL)]] with this representation. LILAC is based on the following three key ideas:
 * <b>Lifelong learning</b>: LILAC can learn from experiences gathered over time, even if the environment changes. This is because LILAC learns a representation of the environment that is invariant to small changes.
-* <b>Latent variable models</b>: LILAC uses latent variable models to learn a compact representation of the environment. This representation captures the underlying structure of the environment, which makes it easier for LILAC to learn to act optimally.
+* <b>Latent variable models</b>: LILAC uses [[latent]] variable models to learn a compact representation of the environment. This representation captures the underlying structure of the environment, which makes it easier for LILAC to learn to act optimally.
-* <b>Maximum entropy policy</b>: LILAC uses a maximum entropy policy, which is a policy that is as diverse as possible. This makes LILAC more robust to changes in the environment, and also helps it to explore new and potentially better policies.
+* <b>Maximum entropy policy</b>: LILAC uses a maximum entropy [[policy]], which is a [[policy]] that is as diverse as possible. This makes LILAC more robust to changes in the environment, and also helps it to explore new and potentially better [[Policy|policies]].
-LILAC has been shown to outperform state-of-the-art [[Reinforcement Learning|RL algorithms]] on a variety of simulated environments that exhibit lifelong non-stationarity. For example, LILAC was able to learn to navigate a maze that changes over time, and to learn to play a game against an opponent who is constantly adapting.
+LILAC has been shown to outperform state-of-the-art [[Reinforcement Learning|RL algorithms]] on a variety of simulated environments that exhibit lifelong non-stationarity. For example, LILAC was able to learn to navigate a maze that changes over time, and to learn to play a game against an opponent who is constantly adapting. LILAC is a promising [[Reinforcement Learning|RL algorithm]] that has the potential to be used in a wide range of applications, such as robotics, autonomous driving, and finance. Here are some examples of how LILAC could be used in the real world:
 * A robot that uses LILAC could learn to navigate a changing environment, such as a warehouse where the shelves are constantly being moved around.

@@ Line 25: / Line 25: @@
 * [[Policy]]   ... [[Policy vs Plan]] ... [[Constitutional AI]] ... [[Trust Region Policy Optimization (TRPO)]] ... [[Policy Gradient (PG)]] ... [[Proximal Policy Optimization (PPO)]]
 Researchers from [https://ai.stanford.edu/ Stanford AI Lab (SAIL)] have devised a method to deal with data and environments that change over time in a way that outperforms some leading approaches to reinforcement learning. Lifelong Latent Actor-Critic, aka LILAC, uses latent variable models and a maximum entropy policy to leverage past experience for better sample efficiency and performance in dynamic environments. [https://venturebeat.com/2020/07/01/stanford-ai-researchers-introduce-lilac-reinforcement-learning-for-dynamic-environments/ Stanford AI researchers introduce LILAC, reinforcement learning for dynamic environments | Khari Johnson - VentureBeat]
 == Continuous Action ==

@@ Line 23: / Line 23: @@
 *** Lifelong Latent Actor-Critic (LILAC)
 ** [[Hierarchical Reinforcement Learning (HRL)]]
+* [[Policy]]   ... [[Policy vs Plan]] ... [[Constitutional AI]] ... [[Trust Region Policy Optimization (TRPO)]] ... [[Policy Gradient (PG)]] ... [[Proximal Policy Optimization (PPO)]]
 Researchers from [https://ai.stanford.edu/ Stanford AI Lab (SAIL)] have devised a method to deal with data and environments that change over time in a way that outperforms some leading approaches to reinforcement learning. Lifelong Latent Actor-Critic, aka LILAC, uses latent variable models and a maximum entropy policy to leverage past experience for better sample efficiency and performance in dynamic environments. [https://venturebeat.com/2020/07/01/stanford-ai-researchers-introduce-lilac-reinforcement-learning-for-dynamic-environments/ Stanford AI researchers introduce LILAC, reinforcement learning for dynamic environments | Khari Johnson - VentureBeat]

@@ Line 5: / Line 5: @@
 |description=Helpful resources for your journey with artificial intelligence; videos, articles, techniques, courses, profiles, and tools
 }}
-[http://www.youtube.com/results?search_query=Lifelong+Latent+Actor+Critic+LILAC+Reinforcement+Machine+Learning YouTube search...]
+[https://www.youtube.com/results?search_query=Lifelong+Latent+Actor+Critic+LILAC+Reinforcement+Machine+Learning YouTube search...]
-[http://www.google.com/search?q=Lifelong+Latent+Actor+Critic+LILAC+Reinforcement+Machine+Learning ...Google search]
+[https://www.google.com/search?q=Lifelong+Latent+Actor+Critic+LILAC+Reinforcement+Machine+Learning ...Google search]
 * [[Lifelong Learning]]
@@ Line 25: / Line 25: @@
-Researchers from [http://ai.stanford.edu/ Stanford AI Lab (SAIL)] have devised a method to deal with data and environments that change over time in a way that outperforms some leading approaches to reinforcement learning. Lifelong Latent Actor-Critic, aka LILAC, uses latent variable models and a maximum entropy policy to leverage past experience for better sample efficiency and performance in dynamic environments. [http://venturebeat.com/2020/07/01/stanford-ai-researchers-introduce-lilac-reinforcement-learning-for-dynamic-environments/ Stanford AI researchers introduce LILAC, reinforcement learning for dynamic environments | Khari Johnson - VentureBeat]
+Researchers from [https://ai.stanford.edu/ Stanford AI Lab (SAIL)] have devised a method to deal with data and environments that change over time in a way that outperforms some leading approaches to reinforcement learning. Lifelong Latent Actor-Critic, aka LILAC, uses latent variable models and a maximum entropy policy to leverage past experience for better sample efficiency and performance in dynamic environments. [https://venturebeat.com/2020/07/01/stanford-ai-researchers-introduce-lilac-reinforcement-learning-for-dynamic-environments/ Stanford AI researchers introduce LILAC, reinforcement learning for dynamic environments | Khari Johnson - VentureBeat]
 == Continuous Action ==

@@ Line 9: / Line 9: @@
 * [[Lifelong Learning]]
-* [[Reinforcement Learning (RL)]]:
+* [[Reinforcement Learning (RL)]]
 ** [[Monte Carlo]] (MC) Method - Model Free Reinforcement Learning
 ** [[Markov Decision Process (MDP)]]
 ** [[Q Learning]]
-** [[State-Action-Reward-State-Action (SARSA)]]
+*** [[Deep Q Network (DQN)]]
 ** [[Deep Reinforcement Learning (DRL)]] DeepRL
 ** [[Distributed Deep Reinforcement Learning (DDRL)]]
 ** [[Evolutionary Computation / Genetic Algorithms]]
 ** [[Actor Critic]]
 *** [[Advanced Actor Critic (A2C)]]
 *** Lifelong Latent Actor-Critic (LILAC)
 ** [[Hierarchical Reinforcement Learning (HRL)]]
 Researchers from [http://ai.stanford.edu/ Stanford AI Lab (SAIL)] have devised a method to deal with data and environments that change over time in a way that outperforms some leading approaches to reinforcement learning. Lifelong Latent Actor-Critic, aka LILAC, uses latent variable models and a maximum entropy policy to leverage past experience for better sample efficiency and performance in dynamic environments. [http://venturebeat.com/2020/07/01/stanford-ai-researchers-introduce-lilac-reinforcement-learning-for-dynamic-environments/ Stanford AI researchers introduce LILAC, reinforcement learning for dynamic environments | Khari Johnson - VentureBeat]

← Older revision		Revision as of 20:00, 3 July 2020
Line 25:		Line 25:

	Researchers from [http://ai.stanford.edu/ Stanford AI Lab (SAIL)] have devised a method to deal with data and environments that change over time in a way that outperforms some leading approaches to reinforcement learning. Lifelong Latent Actor-Critic, aka LILAC, uses latent variable models and a maximum entropy policy to leverage past experience for better sample efficiency and performance in dynamic environments. [http://venturebeat.com/2020/07/01/stanford-ai-researchers-introduce-lilac-reinforcement-learning-for-dynamic-environments/ Stanford AI researchers introduce LILAC, reinforcement learning for dynamic environments \| Khari Johnson - VentureBeat]		Researchers from [http://ai.stanford.edu/ Stanford AI Lab (SAIL)] have devised a method to deal with data and environments that change over time in a way that outperforms some leading approaches to reinforcement learning. Lifelong Latent Actor-Critic, aka LILAC, uses latent variable models and a maximum entropy policy to leverage past experience for better sample efficiency and performance in dynamic environments. [http://venturebeat.com/2020/07/01/stanford-ai-researchers-introduce-lilac-reinforcement-learning-for-dynamic-environments/ Stanford AI researchers introduce LILAC, reinforcement learning for dynamic environments \| Khari Johnson - VentureBeat]
		+
		+	== Continuous Action ==
		+
		+	<youtube>kWHSH2HgbNQ</youtube>
		+	<youtube>G0L8SN02clA</youtube>

← Older revision		Revision as of 19:52, 3 July 2020
Line 23:		Line 23:
	** [[Hierarchical Reinforcement Learning (HRL)]]		** [[Hierarchical Reinforcement Learning (HRL)]]

−	Researchers from Stanford AI Lab (SAIL) have devised a method to deal with data and environments that change over time in a way that outperforms some leading approaches to reinforcement learning. Lifelong Latent Actor-Critic, aka LILAC, uses latent variable models and a maximum entropy policy to leverage past experience for better sample efficiency and performance in dynamic environments. [http://venturebeat.com/2020/07/01/stanford-ai-researchers-introduce-lilac-reinforcement-learning-for-dynamic-environments/ Stanford AI researchers introduce LILAC, reinforcement learning for dynamic environments \| Khari Johnson - VentureBeat]	+	Researchers from [http://ai.stanford.edu/ Stanford AI Lab (SAIL)] have devised a method to deal with data and environments that change over time in a way that outperforms some leading approaches to reinforcement learning. Lifelong Latent Actor-Critic, aka LILAC, uses latent variable models and a maximum entropy policy to leverage past experience for better sample efficiency and performance in dynamic environments. [http://venturebeat.com/2020/07/01/stanford-ai-researchers-introduce-lilac-reinforcement-learning-for-dynamic-environments/ Stanford AI researchers introduce LILAC, reinforcement learning for dynamic environments \| Khari Johnson - VentureBeat]