Popular-RL-Algorithms
PyTorch implementation of Soft Actor-Critic (SAC), Twin Delayed DDPG (TD3), Actor-Critic (AC/A2C), Proximal Policy Optimization (PPO), QT-Opt, PointNet..
- 1.4k
- Jupyter Notebook
- Apache-2.0
- 21 mo ago
quantumiracle
PhD at ECE Dept. Princeton University | MSc of ML at Imperial College London | Intern @ Meta GenAI&FAIR @Adobe @ BorealisAI @ Tencent Robotics X @ Inspir.ai
Built from quantumiracle's public GitHub profile, Princeton. Not on Take My Repo yet, so there are no posts or updates here.
PyTorch implementation of Soft Actor-Critic (SAC), Twin Delayed DDPG (TD3), Actor-Critic (AC/A2C), Proximal Policy Optimization (PPO), QT-Opt, PointNet..
Apply deep reinforcement learning methods including DQN, DDPG for traffic light control in simulation (discrete environment), to prove the 'Green Wave' phenomenon in intelligent traffic system.
Q-network with cross-entropy (CE) method for reinforcement learning.
MARS is shortened for Multi-Agent Research Studio, a library for mulit-agent reinforcement learning research.
Open-source code for paper CDT: Cascading Decision Trees for Explainable Reinforcement Learning
Benchmark present methods for efficient reinforcement learning. Methods include Reptile, MAML, Residual Policy, etc. RL algorithms include DDPG, PPO.
Official implementation for: Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learning ICLR'24
Official code (simulation part) for paper Sim-to-Real Transfer for Robotic Manipulation with Tactile Sensory Zihan Ding, Ya-Yen Tsai, Wang Wei Lee, Bidan Huang International Conference on Intelligent Robots and Systems (IROS) 2021
Official code of Nash-DQN for paper: Nash-DQN algorithm for two-player zero-sum Markov games, details see our paper: A Deep Reinforcement Learning Approach for Finding Non-Exploitable Strategies in Two-Player Atari Games. Zihan Ding, Dijia Su, Qinghua Liu, Chi Jin
Sigle qubit state discrimination with machine learning method (neural networks); An on board implementation with vivado FPGA + ARM, for fast qubit discrimination and feedback control in real physics system.
Official implementation of "Diffusion World Model: Future Modeling Beyond Step-by-Step Rollout for Offline Reinforcement Learning" (arXiv:2402.03570)
Code for paper Not Only Domain Randomization: Universal Policy with Embedding System Identification.