kelvinksau/poca-SoccerTwos
Reinforcement Learning
•
Updated
Ka Sing (Kelvin) Au
kelvinksau
·
AI & ML interests
implement applications leveraging Generative AI models, such as OpenAI GPT, and Meta Llama2/3, focusing on enhancing developer and business productivity with LLM enhancement like KV-Cache, Rotary Positional Embedding, RMS Norm, Grouped Query Attention, SwiGLU, and Flash Attention.
Organizations
None yet
models
16
kelvinksau/ppo-LunarLander-v2
Reinforcement Learning
•
Updated
kelvinksau/ppo-PyramidsRND
Reinforcement Learning
•
Updated
•
1
kelvinksau/ppo-SnowballTarget
Reinforcement Learning
•
Updated
kelvinksau/ppo-CartPole-v1
Reinforcement Learning
•
Updated
kelvinksau/kelvinksau
Updated
kelvinksau/rl_course_vizdoom_health_gathering_supreme
Reinforcement Learning
•
Updated
kelvinksau/a2c-PandaPickAndPlace-v3
Reinforcement Learning
•
Updated
kelvinksau/a2c-PandaReachDense-v3
Reinforcement Learning
•
Updated
kelvinksau/dqn-SpaceInvadersNoFrameskip-v4
Reinforcement Learning
•
Updated
datasets
0
None public yet