arxiv:2410.13232
Gwanwoo Song
Gwanwoo
AI & ML interests
Reinforcement Learning & Robot Learning
Recent Activity
updated a dataset 9 days ago
Gwanwoo/ogbench-cube-quadruple-play-100m-v0 updated a dataset 10 days ago
Gwanwoo/ogbench-antmaze-large-navigate-v0 published a dataset 10 days ago
Gwanwoo/ogbench-antmaze-large-navigate-v0Organizations
None yet
models 10
Gwanwoo/rm_news
95.8M • Updated • 4
Gwanwoo/align_llama
Text Generation • 1B • Updated • 9
Gwanwoo/dpo_orca-dpo_lr1e-5
Updated
Gwanwoo/sft-llama3-1b-lora-adapter_35k
Updated
Gwanwoo/sft-qwen2-0.5b-lora-adapter
Updated
Gwanwoo/filtering_w_noise
Updated
Gwanwoo/tokenizer_final
Updated
Gwanwoo/llama_3.2_kor_lowppe_tokenizer
Updated
Gwanwoo/korean_tokenizer_cleaned_model
Updated
Gwanwoo/really_naive
Updated
datasets 21
Gwanwoo/ogbench-cube-quadruple-play-100m-v0
Updated • 444
Gwanwoo/ogbench-cube-triple-play-100m-v0
Updated • 329
Gwanwoo/ogbench-antmaze-large-navigate-v0
Updated • 68
Gwanwoo/ogbench-puzzle-4x4-play-v0
Updated • 65
Gwanwoo/ogbench-puzzle-3x3-play-v0
Updated • 63
Gwanwoo/ogbench-scene-play-v0
Updated • 61
Gwanwoo/ogbench-humanoidmaze-medium-navigate-v0
Updated • 60
Gwanwoo/ogbench-humanoidmaze-large-navigate-v0
Updated • 55
Gwanwoo/ogbench-cube-double-play-v0
Updated • 69
Gwanwoo/ogbench-antmaze-giant-navigate-v0
Updated • 50