kennyderek

adap

Adaptable Agent Populations via a Generative Model of Policies

dh-website

A site for MIT cultural community cooking systems

kennyderek.github.io

object-choice-prediction

Class final project comparing probabilistic model to human intuition of action prediction.

pytorch-maml-rl

Reinforcement Learning with Model-Agnostic Meta-Learning in Pytorch

reptile-rl

REPTILE for Deep Reinforcement Learning with actor-critic policy gradient using PPO

ROS_bots

Uses 2 different ROS nodes; one creates the desired number of 'bots', the other prints their locations

smooth_trajectory

A demonstration of how to use Rviz and ROS to create a trajectory with randomized error and corresponding smoothed trajectory.

stable-baselines3

PyTorch version of Stable Baselines, improved implementations of reinforcement learning algorithms.

kennyderek/adap

Adaptable Agent Populations via a Generative Model of Policies

kennyderek/reptile-rl

REPTILE for Deep Reinforcement Learning with actor-critic policy gradient using PPO

kennyderek/dh-website

A site for MIT cultural community cooking systems

kennyderek/kennyderek.github.io

kennyderek/object-choice-prediction

Class final project comparing probabilistic model to human intuition of action prediction.

kennyderek/pytorch-maml-rl

Reinforcement Learning with Model-Agnostic Meta-Learning in Pytorch

kennyderek/ROS_bots

Uses 2 different ROS nodes; one creates the desired number of 'bots', the other prints their locations

kennyderek/smooth_trajectory

A demonstration of how to use Rviz and ROS to create a trajectory with randomized error and corresponding smoothed trajectory.

kennyderek/stable-baselines3

PyTorch version of Stable Baselines, improved implementations of reinforcement learning algorithms.