facebear-ljx Goto Github PK

bearrobot

My robot learning repo

bridge_data_v2

decision-pretrained-transformer

Implemention of the Decision-Pretrained Transformer (DPT) from the paper Supervised Pretraining Can Learn In-Context Reinforcement Learning.

decision-transformer

Official codebase for Decision Transformer: Reinforcement Learning via Sequence Modeling.

doge

The official implementation of "When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement Learning" (ICLR2023)

facebear-ljx.github.io

My personal homepage

fisor

[ICLR 2024] The official implementation of "Feasibility-Guided Safe Offline Reinforcement Learning"

fsrl

🚀 A fast safe reinforcement learning library in PyTorch

ivr

Author's implementation of SQL and EQL in "Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization"

proto

rgm

The official implementation of "Mind the Gap: Offline Policy Optimization for Imperfect Rewards" (ICLR2023)

sbac

Facebear's minimal implementation of SBAC (Soft behavior regularized actor critic, NIPS22 offline RL workshop)