liuqi8827 Goto Github PK

trust_ddpg

Trust Region constrained updates for DDPG

understanding-rl-vision

Code for the paper "Understanding RL Vision"

unreal

Reinforcement learning with unsupervised auxiliary tasks

unreal-1

Reinforcement learning with unsupervised auxiliary tasks

unscalable-heuristic-approximator

Deep learning/Reinforcement Learning methods for A*

url_benchmark

valor

Implementation of VALOR (Variational Option Discovery Algorithms)

valueestimationrl

Compute Q-Value Estimation for RL in MuJoCo environment.

vdm

Code for "Variational Dynamic for Self-Supervised Exploration in Deep Reinforcement Learning"

vinet

VINet: Visual-Inertial Odometry as a Sequence-to-Sequence Learning Problem

visual-explanation-in-deep-reinforcement-learning

This project visualizes the knowledge of an agent trained by Deep Reinforcement Learning (paper will be published) using Backpropagation, Guided Backpropagation, GradCam and Guided gradCam. It shows why the agent is performing the action. Which pixels had the biggest influence on the decision of the agent.

visual_marl

The visualization of a multi-agent reinforcement learning (MARL)-based strategy with efficient exploration strategy.

wassersteintsne

wechat-deleted-friends

查看被删的微信好友

why-clipping-accelerates

A pytorch implementation for the LSTM experiments in the paper: Why Gradient Clipping Accelerates Training: A Theoretical Justification for Adaptivity

world_models