The document discusses analyzing correlation networks between Scottish whisky distilleries. A correlation matrix is created from sensory characteristics of whiskies. This is converted to a graph object where nodes are distilleries and edges represent correlations above 0.8. The graph is analyzed to find clustering of distilleries based on sensory profiles and key central nodes. Visualizations of the network are also created.
This document discusses generative adversarial networks (GANs) and their relationship to reinforcement learning. It begins with an introduction to GANs, explaining how they can generate images without explicitly defining a probability distribution by using an adversarial training process. The second half discusses how GANs are related to actor-critic models and inverse reinforcement learning in reinforcement learning. It explains how GANs can be viewed as training a generator to fool a discriminator, similar to how policies are trained in reinforcement learning.
1) The document discusses recent advances in deep reinforcement learning algorithms for continuous control tasks. It examines factors like network architecture, reward scaling, random seeds, environments and codebases that impact reproducibility of deep RL results.
2) It analyzes the performance of algorithms like ACKTR, PPO, DDPG and TRPO on benchmarks like Hopper, HalfCheetah and identifies unstable behaviors and unfair comparisons.
3) Simpler approaches like nearest neighbor policies are explored as alternatives to deep networks for solving continuous control tasks, especially in sparse reward settings.
This document discusses generative adversarial networks (GANs) and their relationship to reinforcement learning. It begins with an introduction to GANs, explaining how they can generate images without explicitly defining a probability distribution by using an adversarial training process. The second half discusses how GANs are related to actor-critic models and inverse reinforcement learning in reinforcement learning. It explains how GANs can be viewed as training a generator to fool a discriminator, similar to how policies are trained in reinforcement learning.
1) The document discusses recent advances in deep reinforcement learning algorithms for continuous control tasks. It examines factors like network architecture, reward scaling, random seeds, environments and codebases that impact reproducibility of deep RL results.
2) It analyzes the performance of algorithms like ACKTR, PPO, DDPG and TRPO on benchmarks like Hopper, HalfCheetah and identifies unstable behaviors and unfair comparisons.
3) Simpler approaches like nearest neighbor policies are explored as alternatives to deep networks for solving continuous control tasks, especially in sparse reward settings.
This slide is used in study class in Web application circle in Waseda University.
And This slide is based on
"Introduction to Machine Learning with Python"