dmksjfl

CABI

code for Double Check Your State Before Trusting It: Confidence-Aware Bidirectional Offline Model-Based Imagination (NeurIPS 2022)

DARC

Code for Efficient Continuous Control with Double Actors and Regularized Critics, AAAI 2022.

GD3

This is the repository of Generalized-activated Deep Deouble Deterministic Policy Gradients (GD3).

Job_Shop_Scheduling_Problem_with_Reinforcement_Learning

This is the implemention of JSSP with RL. The framework used for RL is actor critic and the dataset comes from Tianchi competition.

MCQ

Code for Mildly Conservative Q-learning for Offline Reinforcement Learning (NeurIPS 2022)

PAR

Official code for Cross-Domain Policy Adaptation by Capturing Representation Mismatch (ICML 2024)

SACMPC

SAC+TDMPC

SAW

Code for State Advantage Weighting for Offline RL

SEABO

Official code for ICLR 2024 paper, SEABO: A Simple Search-Based Method for Offline Imitation Learning

SMR

sample multiple reuse

dmksjfl/Job_Shop_Scheduling_Problem_with_Reinforcement_Learning

This is the implemention of JSSP with RL. The framework used for RL is actor critic and the dataset comes from Tianchi competition.

dmksjfl/MCQ

Code for Mildly Conservative Q-learning for Offline Reinforcement Learning (NeurIPS 2022)

dmksjfl/DARC

Code for Efficient Continuous Control with Double Actors and Regularized Critics, AAAI 2022.

dmksjfl/PAR

Official code for Cross-Domain Policy Adaptation by Capturing Representation Mismatch (ICML 2024)

dmksjfl/SEABO

Official code for ICLR 2024 paper, SEABO: A Simple Search-Based Method for Offline Imitation Learning

dmksjfl/CABI

code for Double Check Your State Before Trusting It: Confidence-Aware Bidirectional Offline Model-Based Imagination (NeurIPS 2022)

dmksjfl/GD3

This is the repository of Generalized-activated Deep Deouble Deterministic Policy Gradients (GD3).

dmksjfl/SACMPC

SAC+TDMPC

dmksjfl/SAW

Code for State Advantage Weighting for Offline RL

dmksjfl/SMR

sample multiple reuse

dmksjfl/THU-Homework-LaTex-Template

This is a LaTex template for THU homework which is suitable for math/physics/statistics/computer science and other related majors. This template is simple and may not meet all of your needs where you should improve it yourself.

dmksjfl/BCQ

Author's PyTorch implementation of BCQ for continuous and discrete actions

dmksjfl/ChainsawManGunDemon

This is a complement of Gun Demon in manga Chainsaw Man by Fujimoto Hiroshi. One could find the source of manga in JUMP.

dmksjfl/digit_num_recog

None

dmksjfl/dmksjfl.github.io

Personal academic website

dmksjfl/O2O-coupon-use-prediction

This is an implement of o2o coupon use prediction competition in Tianchi. You could find more infomation there. We get a score of 0.6377 with pure offline dataset.

dmksjfl/RL_for_video_hash