DylanCope

Evolving-Protozoa

An interactive environment where protozoa-like entities live, die, and have offspring whose behaviours and morphologies can change.

Image-Captioning-with-Bimodal-Transformers

Notebook implementing a custom bimodal transformer architecture for masked language modelling in order to learn to caption COCO images.

IPCV-Summary

Summary and Implementations of the content of the University of Bristol Image Processing and Computer Vision course.

llm-steering

Multi-Agent-RL-with-TF

Training intrinsically motivated, independent Q-learners to play Tic-Tac-Toe

NeuroEvolution

Implementation and experimentation centred around the algorithm "NeuroEvolution of Augmenting Topologies"

ProtoEvo

An interactive real-time simulation for evolving multicellular organisms.

reproducible_figures

Small utility for creating reproducible figures with matplotlib

rllib_emecom

Emergent Communication in RLlib

zero-shot-comm

Source code for our paper "Learning to Communicate with Strangers via Channel Randomisation Methods"

DylanCope/Evolving-Protozoa

An interactive environment where protozoa-like entities live, die, and have offspring whose behaviours and morphologies can change.

DylanCope/ProtoEvo

An interactive real-time simulation for evolving multicellular organisms.

DylanCope/Multi-Agent-RL-with-TF

Training intrinsically motivated, independent Q-learners to play Tic-Tac-Toe

DylanCope/Image-Captioning-with-Bimodal-Transformers

Notebook implementing a custom bimodal transformer architecture for masked language modelling in order to learn to caption COCO images.

DylanCope/reproducible_figures

Small utility for creating reproducible figures with matplotlib

DylanCope/rllib_emecom

Emergent Communication in RLlib

DylanCope/dylancope.github.io

DylanCope/Entropy-Masking-OOD

DylanCope/kc-evo-sim

DylanCope/llm-steering

DylanCope/MinecraftAutosplit

DylanCope/zero-shot-comm

Source code for our paper "Learning to Communicate with Strangers via Channel Randomisation Methods"

DylanCope/agents

TF-Agents is a library for Reinforcement Learning in TensorFlow

DylanCope/concordia

A library for generative social simulation

DylanCope/gym-maze

A basic 2D maze environment where an agent start from the top left corner and try to find its way to the bottom left corner.

DylanCope/Image-Autoencoding

Small reference notebook for creating an image autoencoder with Keras

DylanCope/image-interpolating

DylanCope/jax-neural-density-estimation

DylanCope/LaTex-Presentation-Learning-to-Communicate-with-Strangers

DylanCope/learning-translations

DylanCope/LiveSplit.Minecraft

DylanCope/ML-CW

Implementing and evaluating a Naive Bayes spam filter

DylanCope/multiagent-envs

Adapted codebase from "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"

DylanCope/ProtoEvo-Animations

DylanCope/ray

Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

DylanCope/reconhub.github.io

Official website for RECON - The R Epidemics CONsortium

DylanCope/safety-gym

Tools for accelerating safe exploration research. Forked to make compatible with dm mujoco release (WIP)

DylanCope/sequential_social_dilemma_games

Repo for reproduction of sequential social dilemmas

DylanCope/SGD-Animations

DylanCope/TF-Docker-Project-Creator