idthanm
I am currently a Ph.D. candidate at Tsinghua University, Beijing, China. I am working on advanced technologies in autonomous driving and reinforcement learning.
Tsinghua Univ.Beijing, China
Pinned Repositories
admm_adp
baselines_sil
baselines_toyota_2018
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
env_build
The repo develops a general and extensible RL environment for large-scale autonomous driving tasks.
exp4dirl
h-DDPG
idthanm.github.io
mpg
MPG is originated from the paper "Mixed policy gradient", which also contains a cluster of high-quality implementations of deep reinforcement learning algorithms.
ray
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
experiment_driving
Real Vehicle Experiment for Integrated decision and control framwork
idthanm's Repositories
idthanm/env_build
The repo develops a general and extensible RL environment for large-scale autonomous driving tasks.
idthanm/mpg
MPG is originated from the paper "Mixed policy gradient", which also contains a cluster of high-quality implementations of deep reinforcement learning algorithms.
idthanm/baselines_sil
idthanm/baselines_toyota_2018
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
idthanm/exp4dirl
idthanm/h-DDPG
idthanm/idthanm.github.io
idthanm/admm_adp
idthanm/apex_sac
idthanm/baselines4dsac
idthanm/dm_control
The DeepMind Control Suite and Package
idthanm/dopamine
Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.
idthanm/dreamer
Dream to Control: Learning Behaviors by Latent Imagination
idthanm/dreamerv2
Mastering Atari with Discrete World Models
idthanm/GamestonkTerminal
The next best thing after Bloomberg Terminal
idthanm/handful-of-trials
Experiment code for "Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models"
idthanm/Intersections
For toyota project
idthanm/mbpo
Code for the paper "When to Trust Your Model: Model-Based Policy Optimization"
idthanm/mbrl-lib
Library for Model Based RL
idthanm/obstacle-tower-challenge
Starter Kit for the Unity Obstacle Tower challenge
idthanm/obstacle-tower-env
Obstacle Tower Environment
idthanm/otc
used for the competition
idthanm/ray
A fast and simple framework for building and running distributed applications.
idthanm/TRARS