zr-obp
Off-policy eval
A framework for off-policy evaluation and learning in multi-armed bandit algorithms
Open Bandit Pipeline: a python library for bandit algorithms and off-policy evaluation
645 stars
88 watching
88 forks
Language: Python
last commit: 6 months ago
Linked from 1 awesome list
contextual-banditsdatasetsmulti-armed-banditsoff-policy-evaluationresearch
hanjuku-kaso/awesome-offline-rlRelated projects:
| Repository | Description | Stars |
|---|---|---|
 clvoloshin/cobs | A toolkit for evaluating and analyzing off-policy policy estimation methods in reinforcement learning | 61 |
 onlytailei/carla_cil_pytorch | Implementation of a conditional imitation learning policy in PyTorch for autonomous driving using the Carla dataset. | 66 |
 matrix-org/rust-opa-wasm | A Rust SDK to evaluate Open Policy Agent policies in WebAssembly format. | 48 |
 zzhanghub/eval-co-sod | An evaluation tool for co-saliency detection tasks | 96 |
 google-research/dice_rl | This library provides tools and algorithms for estimating the distribution correction in off-policy reinforcement learning problems | 99 |
 sony/pyieoe | Develops an interpretable evaluation procedure for off-policy evaluation (OPE) methods to quantify their sensitivity to hyper-parameter choices and/or evaluation policy choices. | 31 |
 a2d24/python-opa-wasm | A Python SDK for executing and managing Open Policy Agent policies in WebAssembly format | 10 |
 psecio/propauth | Evaluates policies against user credentials and properties to determine access permissions. | 59 |
 oeg-upm/lubm4obda | Evaluates Ontology-Based Data Access systems with inference and meta knowledge benchmarking | 4 |
 resibots/blackdrops | An open-source policy search algorithm for robotics that uses Gaussian processes to model robot dynamics and accounts for uncertainty. | 64 |
 netflix-skunkworks/policyuniverse | A Python package for parsing and processing AWS IAM policies and statements. | 428 |
 denisyarats/exorl | Provides exploratory data and algorithms for offline reinforcement learning in various control domains | 105 |
 demisto/cops | Standardized framework for creating and sharing incident response processes in a shared language | 150 |
 lartpang/pysodevaltoolkit | A comprehensive Python toolbox for evaluating salient object detection and camouflaged object detection tasks | 167 |
 hubfire/muti-branch-ddpg-carla | An implementation of a reinforcement learning algorithm using multi-branch architecture and Deep Deterministic Policy Gradients (DDPG) to control autonomous vehicles in simulation environments. | 79 |