aviralkumar2907

models

Models and examples built with TensorFlow

rllab

rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.

rlkit

Collection of reinforcement learning algorithms

EasyLM

Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.

distributional-dqn

Implementation of 'A Distributional Perspective on Reinforcement Learning' and 'Distributional Reinforcement Learning with Quantile Regression' based on OpenAi DQN baselines.

CQL

Conservative Q Learning on top of SAC

Cal-QL

official implementation for our paper Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning

doodad

A job launching library for docker, EC2, GCP, etc.

JaxCQL

Conservative Q learning in Jax

design-bench

PTR

This repository contains the implementation of the PTR algorithm described in the paper: Pre-Training for Robots: Leveraging Diverse Multitask Data via Offline Reinforcement Learning.

design-baselines

diagnosing_qlearning

Code for Diagnosing Bottlenecks in Deep Q-learning. Contains implementations of tabular environments plus solvers.

SimpleSAC

A simple and easy to use implementation of the soft actor-critic algorithm.

parameterized_model

TensorFlow parameterized model library

rlutil