Deep RL Models
🏗️ Building on HF
Ryan Tran
ryanhoangt
AI & ML interests
Robot Learning, LLMs & Agents, NLP
Recent Activity
updated a dataset about 8 hours ago
ryanhoangt/browsecomp-plus-qwen3-0.6b published a dataset about 8 hours ago
ryanhoangt/browsecomp-plus-qwen3-0.6b updated a model 15 days ago
ryanhoangt/pi05_libero_pytorch_drvlaOrganizations
models 48
ryanhoangt/pi05_libero_pytorch_drvla
4B • Updated • 45
ryanhoangt/ra-vla-official-assets
Updated
ryanhoangt/Qwen3-8B-Open-R1-GRPO
8B • Updated • 5
ryanhoangt/pi05_base
Updated
ryanhoangt/pi05_libero
Updated
ryanhoangt/DeepSeek-R1-Distill-Qwen-7B_pruned_40_prunemethod_SparseGPT_dataset_trace_OpenR1-Math-220k
8B • Updated • 6
ryanhoangt/sam2
Updated
ryanhoangt/pi0_fast_libero_icl_30k_all_ckpts
Updated
ryanhoangt/pi0_fast_libero_icl_15k_all_ckpts
Updated
ryanhoangt/pi0_fast_libero
Updated
datasets 39
ryanhoangt/browsecomp-plus-qwen3-0.6b
Viewer • Updated • 100k
ryanhoangt/interp-for-vla-assets-migration
Updated • 62
ryanhoangt/memskill_alfworld
Preview • Updated • 18
ryanhoangt/libero-icl-finetune-plus-90
Franka Panda • Updated • 4.82k episodes • 86
ryanhoangt/libero_90_lerobot_v21
Franka Panda • Updated • 3.96k episodes • 102
ryanhoangt/libero_90_lerobot_v2
Franka Panda • Updated • 3.96k episodes • 149
ryanhoangt/vla-safe-rollouts
Updated • 36
ryanhoangt/ricl-libero-training-processed
Updated • 44
ryanhoangt/ogbench_data
Updated • 792 • 1
ryanhoangt/ABot-PhysWorld_SFT_Training_Data_v1_RoboMIND
Viewer • Updated • 25.1k • 17