Pytorch based reimplementation of COMS: Conservative Objective Models for Effective Offline Model-Based Optimization.
-
Updated
Sep 18, 2023 - Python
Pytorch based reimplementation of COMS: Conservative Objective Models for Effective Offline Model-Based Optimization.
The source code to Cross-Validated Off-Policy Evaluation
PyTorch Implementation of MOPO
Non-modular implementation of common RL algorithms
Implementation of CQL in "Conservative Q-Learning for Offline Reinforcement Learning" based on BRAC family.
Python code to implement hard sampling based task representation learning for robust offline meta RL
Official implementation for "Let Offline RL Flow: Training Conservative Agents in the Latent Space of Normalizing Flows", NeurIPS 2022, Offline RL Workshop
Codes for "Learning from Sparse Offline Datasets via Conservative Density Estimation"
Code for Tackling Long-Horizon Tasks with Model-based Offline Reinforcement Learning
Codes for "Efficient Offline Policy Optimization with a Learned Model", ICLR2023
Original implementations of the VC-FB and MC-FB algorithms from "Zero-Shot Reinforcement Learning from Low Quality Data" by Jeen et. al (2024).
A Production Tool for Embodied AI
Offline Reinforcement Learning Framework in JAX
The easiest way to copy your flight log files and videos from racing drones and goggles DVR.
Implementation of Offline Reinforcement Learning in Gym Mini-Grid Environment 🔑
Benchmark for "Offline Policy Comparison with Confidence"
Codebase for the paper "Efficient Offline Reinforcement Learning: The Critic is Critical"
"S2P: State-conditioned Image Synthesis for Data Augmentation in Offline Reinforcement Learning" (NeurIPS 2022)
Official implementation of "Direct Preference-based Policy Optimization without Reward Modeling" (NeurIPS 2023)
Pytorch implementation of BEAR in "Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction"
Add a description, image, and links to the offline-reinforcement-learning topic page so that developers can more easily learn about it.
To associate your repository with the offline-reinforcement-learning topic, visit your repo's landing page and select "manage topics."