henrycharlesworth
Lead AI Researcher at RevEng.ai. Formerly at Rowden Technologies and before that a postdoc in the WMG data science group, focusing on deep RL research.
United Kingdom
Pinned Repositories
awesome-rl-envs
big2_PPOalgorithm
Application of proximal policy optimization algorithm to the card game Big 2 using Tensorflow
big2_server
Web-app to play against Big 2 agent trained with deep RL.
dexterous-gym
Challenging dexterous manipulation environments for RL that extend the hand manipulation environments introduced in OpenAI's Gym
intrinsically_motivated_collective_motion
Main code for the collective motion model I've been working on during my PhD. Includes some apps made using D3.js to help describe the model.
MonteCarloTreeSearch
Somewhat General MCTS class. c++ standard template library practice.
multi_action_head_PPO
PPO with multi-head/autoregressive action outputs
PlanGAN
SCDM
Solving Complex Dexterous Manipulation Tasks with Trajectory Optimisation and Reinforcement Learning
settlers_of_catan_RL
Learning to play Settlers of Catan with Deep RL - custom training environment and implementation of PPO
henrycharlesworth's Repositories
henrycharlesworth/big2_PPOalgorithm
Application of proximal policy optimization algorithm to the card game Big 2 using Tensorflow
henrycharlesworth/settlers_of_catan_RL
Learning to play Settlers of Catan with Deep RL - custom training environment and implementation of PPO
henrycharlesworth/dexterous-gym
Challenging dexterous manipulation environments for RL that extend the hand manipulation environments introduced in OpenAI's Gym
henrycharlesworth/multi_action_head_PPO
PPO with multi-head/autoregressive action outputs
henrycharlesworth/PlanGAN
henrycharlesworth/SCDM
Solving Complex Dexterous Manipulation Tasks with Trajectory Optimisation and Reinforcement Learning
henrycharlesworth/intrinsically_motivated_collective_motion
Main code for the collective motion model I've been working on during my PhD. Includes some apps made using D3.js to help describe the model.
henrycharlesworth/MonteCarloTreeSearch
Somewhat General MCTS class. c++ standard template library practice.
henrycharlesworth/awesome-rl-envs
henrycharlesworth/big2_server
Web-app to play against Big 2 agent trained with deep RL.
henrycharlesworth/big2online
Multiplayer Implementation of Card Game "Big 2" Using Node.js
henrycharlesworth/henrycharlesworth
Personal profile