- University of Texas at Austin
- hari-sikchi.github.io
- @HariSikchi
Highlights
- Pro
Stars
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
JMLR: OmniSafe is an infrastructural framework for accelerating SafeRL research.
Official code from the paper "Offline RL for Natural Language Generation with Implicit Language Q Learning"
ExORL: Exploratory Data for Offline Reinforcement Learning
The Balloon Learning Environment - flying stratospheric balloons with deep reinforcement learning.
Open-source codebase for EfficientZero, from "Mastering Atari Games with Limited Data" at NeurIPS 2021.
Codebase of NeurIPS 2022 paper ''Planning for Sample Efficient Imitation Learning''
Structural implementation of RL key algorithms
High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC
Code accompanying the paper Adversarially Trained Actor Critic for Offline Reinforcement Learning by Ching-An Cheng*, Tengyang Xie*, Nan Jiang, and Alekh Agarwal.
Benchmarking RL generalization in an interpretable way.
Author's PyTorch implementation of Randomized Ensembled Double Q-Learning (REDQ) algorithm.
(NeurIPS '21 Spotlight) IQ-Learn: Inverse Q-Learning for Imitation
Code for the NeurIPS 2021 paper "Safe Reinforcement Learning by Imagining the Near Future"
Assistive Gym, a physics-based simulation framework for physical human-robot interaction and robotic assistance.
A PyTorch implementation of Implicit Q-Learning
Author's PyTorch implementation of TD3+BC, a simple variant of TD3 for offline RL
Safe Reinforcement Learning through Transferable Instinct Networks
Adapted from the widely used project webpage template made by the colorful folks.
Collection Of Dynamic Morphology Agents For MuJoCo
Benchmarks for Model-Based Optimization