Pinned Repositories
geograph
GeoGraph provides a tool for analysing habitat fragmentation and related problems in landscape ecology. GeoGraph builds a geospatially referenced graph from land cover or field survey data and enables graph-based landscape ecology analysis as well as interactive visualizations.
ai4er-cookiecutter
A quick way to instantiate projects for AI4ER
autoplotlib
Quickly generate plots in Python by simply describing them through text - e.g. use "create a scatter plot with name labels" instead of endlessly searching stackoverflow.
bauwerk
Meta reinforcement learning benchmark with building control environments. An attempt to help scale greener building controllers to more buildings.
beobench
A toolkit providing easy and unified access to building control environments for reinforcement learning (RL). No longer actively maintained.
energym
Energym is an open source building simulation library designed to test climate control and energy management strategies on buildings in a systematic and reproducible way.
gym
A toolkit for developing and comparing reinforcement learning algorithms.
icai
Inverse Constitutional AI: compressing pairwise preference data into a short constitution of principles.
rl-building-control
A curated list of awesome projects applying reinforcement learning (RL) to building control.
solar-agent
This project provides Gym environments to train RL agents to operate batteries in solar-plus-battery installations.
rdnfn's Repositories
rdnfn/beobench
A toolkit providing easy and unified access to building control environments for reinforcement learning (RL). No longer actively maintained.
rdnfn/icai
Inverse Constitutional AI: compressing pairwise preference data into a short constitution of principles.
rdnfn/rl-building-control
A curated list of awesome projects applying reinforcement learning (RL) to building control.
rdnfn/autoplotlib
Quickly generate plots in Python by simply describing them through text - e.g. use "create a scatter plot with name labels" instead of endlessly searching stackoverflow.
rdnfn/solar-agent
This project provides Gym environments to train RL agents to operate batteries in solar-plus-battery installations.
rdnfn/bauwerk
Meta reinforcement learning benchmark with building control environments. An attempt to help scale greener building controllers to more buildings.
rdnfn/ai4er-cookiecutter
A quick way to instantiate projects for AI4ER
rdnfn/energym
Energym is an open source building simulation library designed to test climate control and energy management strategies on buildings in a systematic and reproducible way.
rdnfn/gym
A toolkit for developing and comparing reinforcement learning algorithms.
rdnfn/website
rdnfn/beobench_contrib
Repo for contributions to the beobench package (e.g. gym integrations and experiment definitions).
rdnfn/cookiecutter-pypackage
Cookiecutter template for a Python package.
rdnfn/alpaca_eval
FORK: An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
rdnfn/evalplus
FORK: EvalPlus for rigourous evaluation of LLM-synthesized code
rdnfn/Gymnasium
A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
rdnfn/hugo-cite
📝 Easily manage your bibliography and in-text citations with Hugo, the popular static-site generator.
rdnfn/hugo-PaperMod
A fast, clean, responsive Hugo theme.
rdnfn/lm-evaluation-harness
A framework for few-shot evaluation of autoregressive language models.
rdnfn/MakeAgents
FORK: A Python micro framework for creating LLM-driven agents
rdnfn/minGPT-AML
Fork: A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
rdnfn/mlmi-project
Transcribing MIDI from WAVE - Research project for the MLMI MPhil @ Cambridge (Re-upload April 2021)
rdnfn/practical_sessions_RL
rdnfn/project1-boptest
Building Optimization Performance Tests
rdnfn/project1-boptest-gym
rdnfn/sinergym
Gym environment for building simulation and control using reinforcement learning
rdnfn/SWE-bench
FORK: SWE-Bench: Can Language Models Resolve Real-world Github Issues?