Discovering reinforcement learning algorithms
Reinforcement learning (RL) algorithms update an agent's parameters according to one of
several possible rules, discovered manually through years of research. Automating the …
several possible rules, discovered manually through years of research. Automating the …
Reinforcement learning in games
I Szita - Reinforcement Learning: State-of-the-art, 2012 - Springer
Reinforcement learning and games have a long and mutually beneficial common history.
From one side, games are rich and challenging domains for testing reinforcement learning …
From one side, games are rich and challenging domains for testing reinforcement learning …
Reinforcement learning: An introduction by Richards' Sutton
AG Barto - SIAM Rev, 2021 - SIAM
Reinforcement learning (RL) is a set of mathematical methods and algorithms that can be
applied to a wide array of problems and plays a central role in machine learning. The aim of …
applied to a wide array of problems and plays a central role in machine learning. The aim of …
[图书][B] Statistical reinforcement learning: modern machine learning approaches
M Sugiyama - 2015 - books.google.com
Reinforcement learning is a mathematical framework for developing computer agents that
can learn an optimal behavior by relating generic reward signals with its past actions. With …
can learn an optimal behavior by relating generic reward signals with its past actions. With …
Reinforcement learning and its connections with neuroscience and psychology
Reinforcement learning methods have recently been very successful at performing complex
sequential tasks like playing Atari games, Go and Poker. These algorithms have …
sequential tasks like playing Atari games, Go and Poker. These algorithms have …
Probabilistic policy reuse in a reinforcement learning agent
F Fernández, M Veloso - Proceedings of the fifth international joint …, 2006 - dl.acm.org
We contribute Policy Reuse as a technique to improve a reinforcement learning agent with
guidance from past learned similar policies. Our method relies on using the past policies as …
guidance from past learned similar policies. Our method relies on using the past policies as …
Fast reinforcement learning with generalized policy updates
The combination of reinforcement learning with deep learning is a promising approach to
tackle important sequential decision-making problems that are currently intractable. One …
tackle important sequential decision-making problems that are currently intractable. One …
Reinforcement learning algorithms: A brief survey
Reinforcement Learning (RL) is a machine learning (ML) technique to learn sequential
decision-making in complex problems. RL is inspired by trial-and-error based human/animal …
decision-making in complex problems. RL is inspired by trial-and-error based human/animal …
Agent57: Outperforming the atari human benchmark
Atari games have been a long-standing benchmark in the reinforcement learning (RL)
community for the past decade. This benchmark was proposed to test general competency …
community for the past decade. This benchmark was proposed to test general competency …
Evolving reinforcement learning algorithms
We propose a method for meta-learning reinforcement learning algorithms by searching
over the space of computational graphs which compute the loss function for a value-based …
over the space of computational graphs which compute the loss function for a value-based …