NagisaZj

a3c_continuous

A continuous action space version of A3C LSTM in pytorch plus A3G design

ac-teach

Code for the CoRL 2019 paper AC-Teach: A Bayesian Actor-Critic Method for Policy Learning with an Ensemble of Suboptimal Teachers

arena-hard-auto

Arena-Hard-Auto: An automatic LLM benchmark.

atari-rl

Atari - Deep Reinforcement Learning algorithms in TensorFlow

CUP

IDAQ_Public

learningtolearn

MetaCURE-Public

robosuite

sc2_teacher

NagisaZj/IDAQ_Public

NagisaZj/CUP

NagisaZj/arena-hard-auto

Arena-Hard-Auto: An automatic LLM benchmark.

NagisaZj/bigcode-evaluation-harness

A framework for the evaluation of autoregressive code generation language models.

NagisaZj/ContextWM

Code release for "Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning" (NeurIPS 2023), https://arxiv.org/abs/2305.18499

NagisaZj/decision-transformer

Official codebase for Decision Transformer: Reinforcement Learning via Sequence Modeling.

NagisaZj/diffusion_policy

[RSS 2023] Diffusion Policy Visuomotor Policy Learning via Action Diffusion

NagisaZj/diffusion_reward

[arXiv'23] Official implementation of the paper "Diffusion Reward: Learning Rewards via Conditional Video Diffusion"

NagisaZj/dreamerv3

Mastering Diverse Domains through World Models

NagisaZj/DrM

DrM, a visual RL algorithm, minimizes the dormant ratio to guide exploration-exploitation trade-offs, achieving significant improvements in sample efficiency and asymptotic performance across diverse domains.

NagisaZj/DUP

NagisaZj/evals

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

NagisaZj/Graphormer

Graphormer is a general-purpose deep learning backbone for molecular modeling.

NagisaZj/HIQL

HIQL: Offline Goal-Conditioned RL with Latent States as Actions (NeurIPS 2023)

NagisaZj/hypnettorch

Package for working with hypernetworks in PyTorch.

NagisaZj/icl-alignment

Is In-Context Learning Sufficient for Instruction Following in LLMs?

NagisaZj/implicit_q_learning

NagisaZj/LAPO-offlienRL

NagisaZj/lightATAC

NagisaZj/llama3

The official Meta Llama 3 GitHub site

NagisaZj/metaworld-cup

NagisaZj/MiniGPT-4

Open-sourced codes for MiniGPT-4 and MiniGPT-v2

NagisaZj/mtenv

NagisaZj/octo

Octo is a transformer-based robot policy trained on a diverse mix of 800k robot trajectories.

NagisaZj/OpenRLHF

An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & Mixtral)

NagisaZj/OPPO

NagisaZj/opro

official code for "Large Language Models as Optimizers"

NagisaZj/simple-evals

NagisaZj/universal_manipulation_interface

Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots

NagisaZj/viper_rl

Using advances in generative modeling to learn reward functions from unlabeled videos.