Costa
costa-huang
CS Ph.D student working on reinforcement learning
Teams
Intro
Hello, I'm Costa Huang
👋 Hi, I'm Costa, a Computer Science Ph.D. student at 🎓 Drexel University studying 🕹️Game Artificial Intelligence. My open-sourced work includes some Deep Reinforcement Learning libraries and utility software. 🔥Check out my personal website at https://costa.sh/
Here are some of my open source projects:
- High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
- Create Encrypted Backups of Your Bitwarden Vault with Attachments
- The source code for the blog post The 37 Implementation Details of Proximal Policy Optimization
- A simple and highly efficient RTS-game-inspired environment for reinforcement learning (formerly Gym-MicroRTS)
Reports
Open RL Benchmark 0.6.0
Open source code, open progress, and open reproducibility
12707 views
Last edit 3 years agoAction Guidance: Getting the Best of Sparse Rewards and Shaped Rewards for Real-Time Strategy Games
This is a report illustrating our latest work *Action Guidance: Getting the Best of Sparse Rewards and Shaped Rewards for Real-time Strategy Games* in an interactive manner.
1825 views Last edit 3 years agoGym-pysc2 Benchmark
https://github.com/vwxyzjn/gym-pysc2
909 views Last edit 4 years agoGym-μRTS: Toward Affordable Deep Reinforcement Learning Research in Real-Time Strategy Games
Train agents to play an RTS game with commodity machines (one GPU, three vCPU, 16GB RAM)
8685 views Last edit 3 years agoHow do you reproduce experiments?
1031 views Last edit 4 years agoProjects
Links
Activity
Mon
Wed
Fri
SepOctNovDecJanFebMarAprMayJunJulAug
Runs
Name
Project
State
Created
Loading...