PranavMahajan25

ppc_experiments

modpo

[ACL'2024] Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization.

BetaZero.jl

Belief-state planning for POMDPs using learned approximations

thinker

Thinker project

lerobot

🤗 LeRobot: End-to-end Learning for Real-World Robotics in Pytorch

Implicit-Language-Q-Learning

Official code from the paper "Offline RL for Natural Language Generation with Implicit Language Q Learning"

TD-RL-dynamics

Theory of Temporal Difference Learning Dynamics for High Dimensional Features

VRPainExptGuide

A tutorial guide to be used in the VR pain workshop practical session: https://sites.google.com/view/oxford-vr-workshop/home

HJxB

Continuous-Time/State/Action Fitted Value Iteration via Hamilton-Jacobi-Bellman (HJB)

inverse-optimal-control

Inverse Optimal Control Adapted to the Noise Characteristics of the Human Sensorimotor System

lqg

Inverse optimal control for continuous psychophysics

pyhddmjags

Repository for example Hierarchical Drift Diffusion Model (HDDM) code using JAGS in Python. These scripts provide useful examples for using JAGS with pyjags, the JAGS Wiener module, mixture modeling in JAGS, and Bayesian diagnostics in Python.

OFC4HCI

OFC4HCI – Python Toolbox with Optimal Feedback Control Models for Modeling Human-Computer Interaction (including, e.g., MinJerk, LQR, and LQG)

neuralOFC

Neural Optimal Feedback Control

rlssm

Bayesian Parameter Estimation (based on pystan) of reinforcement learning and sequential sampling models, and combinations of the two.

slir

Python package for Sparse Linear Regression (SLiR)

pybullet-arm-course-public

Interactive lab course intended to teach basic programming principles using simulated robot arms

dma_rl

Decision-Making agents with reinforcement learning

cadrl_ros

ROS package for dynamic obstacle avoidance for ground robots trained with deep RL

tp-rmp

Learning Task-parametrized Riemannian Motion Policies from demonstrations.

robotics-toolbox-python

Robotics Toolbox for Python

rmp2

Code for R:SS 2021 paper RMP2: A Structured Composable Policy Class for Robot Learning.

tactile_gym

Suite of PyBullet reinforcement learning environments targeted towards using tactile data as the main form of observation.

movement_primitives

Dynamical movement primitives (DMPs), probabilistic movement primitives (ProMPs), and spatially coupled bimanual DMPs for imitation learning.

dmpling

Dynamic Movement Primitives in Python

hoi_bhk

HOI testing for the brainhack event 2021

online_var_fil

Code for our paper: Online Variational Filtering and Parameter Learning

SenseAct

SenseAct: A computational framework for developing real-world robot learning tasks

gym

A toolkit for developing and comparing reinforcement learning algorithms.

safe-control-gym

PyBullet CartPole and Quadrotor environments—with CasADi symbolic a priori dynamics—for learning-based control and RL