Today I finally decided to go out, despite the heat. So basically I hopped on bus 91 and here I am in Clearwater bay but it's a pretty good place There is a beautiful beach

AWS published a machine learning blog about how you can finetune Claude 3 Haiku on the Bedrock really easily, and it got me very interested and wanted to set up Haiku to imitate me. Specifically

So following the horrible semester end, came a horrible start of summer. I was gonna join the HKUST research program, but it started very wrong. So I didn't get an exit endorsement for study, or

So anyways, long story short, I started learning and after 3 weeks my new website was born. It just displayed my blogs and visitinfos and a message box. So the problem with frontend+backend+database, where your

https://www.youtube.com/watch?v=qsgs5e6NBPk 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

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'm genuinely grateful for the extraordinary kindness and assistance I received from an airport worker in San Francisco. I was too tired and didn't pay much attention to booking the plane ticket. I booked a

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.