In this note, a demo of a shell-reinforced bending soft pneumatic actuator (SPA) is presented. From the demo, we can have a general idea of the procedures of implicit dynamic analysis using Abaqus....
Temporal-Difference Learning
TD learning is a combination of MC ideas and DP ideas. Like MC methods, TD methods can learn directly from raw experience without a model of the environments dynamics. Like DP, TD methods upd...
Monte Carlo Methods
MC methods are ways of solving RL problem based on averaging sample returns. MC methods sample and average returns for each state-action pair and average rewards for each action. MC methods ...
Dynamic Programming
DP can be used to compute optimal policies given a perfect model of the environment as a MDP. Key idea: use value functions to organize and structure the search for good policies Review: Bellm...
Finite Markov Decision Processes
The Agent-Environment Interface Agent: learner and decision maker Environment: everything outside the agent The agent-environment interaction in a MDP Interaction at discrete time...
Multi-armed Bandits
Tabular Solution Methods Now we consider the simplest forms: the state and action spaces are small enough for the approximate value functions to be represented as arrays, or tables. Multi-arm...
Introduction to Reinforcement Learning
Reinforcement learning is focused on goal-directed learning from interaction. Reinforcement Learning Definition: Reinforcement learning is learning how to map situations to actions so as t...
Autumn in Tsinghua
It has been my third year in Tsinghua, and I finally recorded the autumn here with care. Camera: Minolta SRT Super + 58mm f1.4 Film: Kodak Gold 200 Nature in Autumn Architect...
Film Memories of West Sichuan
Camera: Pentax Espio 120mi Film: Kodak Gold 200 Actually, such dumb cameras are not ideal equipment for landscape. The auto focus does not work well for landscape since the scenery is ...
Landscape in West Sichuan
Mt. Gongga - 贡嘎雪山 Mt. Siguniang - 四姑娘山 Mt. Yala - 雅拉雪山 Starry Night - 星光璀璨