Dhawgupta

jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

args

cmput412-competition1

controllable_agent

dca

Dynamic channel allocation in cellular networks by reinforcement learning

Engine

A library for developing and applying Seldonian algorithms

gupta2021structural

Code for NeurIPS 2021 Paper: Structural Credit Assignment in Neural Networks using Reinforcement Learning

gupta2023behavior

Code for NeurIPS 2023 Spotlight Paper: Behavior Alignment via Reward Function Optimization

gupta2024from

Code for AAAI 2024 Oral: From Past to Future: Rethinking Eligibility Traces

hrldm

Repository and Code for the Heirarchial Reinforcement Learning based Dialogue Management System

i3-config

My awesome i3 configuration

implicit_q_learning

JAXSeq

Train very large language models in Jax.

learn-julia-the-hard-way

Learn Julia the hard way!

LLM_RL

LMRL-Gym

The public repo for changes

muzero-general

MuZero

option-4rooms

option-baselines

option-critic-pytorch

PyTorch implementation of the Option-Critic framework, Harb et al. 2016

personal-webpage

pfqi

purejaxrl

Really Fast End-to-End Jax RL Implementations

pytorch-soft-actor-critic

PyTorch implementation of soft actor critic

quantifying_exposure_bias

Accompanying repository for the paper: Why Exposure Bias Matters: An Imitation Learning Perspective of Error Accumulation in Language Generation

reading

rl-fl

RlGlue

VSCodeFiles

json files and description for my VS code installation

website-data