After getting rid of the crappy UI and installing LineageOS on my Redmi Phone, I was still not satisfied. Mainly because I am using WeChat too frequently, and it is kinda addictive and time-wasting. Those

Today I decided to play around with the BSD distros. I have used many Linux distros and found they are pretty much alike, no big difference anyways except for package managers. Anyways, I hopped on

Recently, the idea of self-hosting was so intriguing that I decided to code a full-stack video platform. There are many Object Storage providers, including Amazon AWS, Akamai, Digital Ocean, Cloudflare, Alibaba Cloud. Nearly all of

I've failed countless times while experimenting with different phones and operating systems. Unlike computers, which have a universal architecture, each phone possesses its unique structure. This makes installing operating systems on them exceedingly challenging. Furthermore,

My front teeth have always been a bit uneven-the upper 2 middle teeth are crowded. Although it didn't cause any pain and I could eat normally, my mom always advised me to get orthodontic treatment

Note: All Yaml files are in the git repo: https://github.com/jimchen2/cs285-reinforcement-learning python cs285/scripts/run_hw5_explore.py \ python cs285/scripts/run_hw5_explore.py \ python cs285/scripts/run_hw5_explore.py \ The Random Network Distillation algorithm encourages exploration by training another neural network to approximate the output

Compute Action and use epsilon greedy action = torch.tensor(random.randint(0, self.num_actions - 1)) action = self.critic(observation).argmax(dim=1) Step environment Add data to replay buffer replay_buffer.insert(...) Sample from replay buffer batch = replay_buffer.sample(config["batch_size"]) Train agent, we update the

There are 2 kinds of estimator for Policy Gradients, full trajectory and and "reward-to-go" We run the two configs on Cartpole with different parameters, specifically, rtg means reward to go, na means normalizing the advantages.

We run imitation learning and Dagger based on expert policies. In this experiment the expert policy is directly sampled out from a trained Neural Network, so Dagger differs from real world applications in that it

Today I visited Ocean Beach. I was in a very bad mood and distorted these days. I couldn't get any work done and think about living in remote, isolated regions. I hopped on a Bart