Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/Cjh327/awesome-my-interests

A curated list of my interested resources.
https://github.com/Cjh327/awesome-my-interests

List: awesome-my-interests

Last synced: 3 months ago
JSON representation

A curated list of my interested resources.

Awesome Lists containing this project

README

        

# Awesome My Interests
A curated list of my interested resources.

## Contents

- [Game AI](#gameai)
- [Human-Centered AI](#hcai)
- [Reinforcement Learning](#reinforcementlearning)
- [Decision Transformer](#decisiontransformer)
- [Big Models for RL](#bigmodelsrl)

## Game AI
### Industrial works
- [DeepMind AlphaStar](https://www.nature.com/articles/s41586-019-1724-z), 2019.
- [OpenAI Five](https://arxiv.org/pdf/1912.06680v1.pdf), 2019.
- [Tencent Juewu](https://arxiv.org/abs/2011.12692), 2020.
- [Learning Diverse Policies in MOBA Games via Macro-Goals](https://arxiv.org/pdf/2110.14221.pdf), 2021.

### Others
- [awesome-game-ai](https://github.com/datamllab/awesome-game-ai) - An awesome library.
- [Game AI Pro](http://www.gameaipro.com/) - Game AI Pro book series.
- [GDC Vault](https://www.gdcvault.com/) - A trove of in-depth design, technical and inspirational talks and slides from the influencers of the game development industry, taken from over 20 years of the worldwide Game Developers Conferences.
- ✅ [AI in Games: Techniques, Challenges and Opportunities](https://arxiv.org/pdf/2111.07631v1.pdf), 2021.
- [Rethinking of AlphaStar](https://arxiv.org/pdf/2108.03452v3.pdf), 2021

## Human-Centered AI
- [Awesome Human-Centered AI (HCAI)](https://github.com/Open-Source-ML/awesome-human-centered-ai) - An awesome library.

## Reinforcement Learning

### Learning Transferable Policies and Representations with Transformer
- [AnyMorph: Learning Transferable Polices By Inferring Agent Morphology](https://arxiv.org/abs/2206.12279), ICML 2022 (Spotlight).
- Related work: [One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Control](https://arxiv.org/abs/2007.04976), ICML 2020.
- [MetaMorph: Learning Universal Controllers with Transformers](https://arxiv.org/abs/2203.11931), 2022.
- [Can Wikipedia Help Offline Reinforcement Learning?](https://arxiv.org/abs/2201.12122), 2022.

### Decision Transformer
- ✅ [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://arxiv.org/abs/2106.01345), 2021.
- ✅ [Offline Reinforcement Learning as One Big Sequence Modeling Problem](https://arxiv.org/abs/2106.02039), 2021.
- ✅ [A Generalist Agent](https://arxiv.org/abs/2205.06175) (Gato), 2022.
-> Use prompt conditioning for multi-task.
- ✅ [GPT,GPT-2,GPT-3 论文精读](https://www.bilibili.com/video/BV1AF411b7xQ/)
- [Online Decision Transformer](https://arxiv.org/abs/2202.05607#facebook), ICML 2022 (Oral).
- ✅ [Multi-Game Decision Transformers](https://arxiv.org/abs/2205.15241), 2022.
- [You Can’t Count on Luck: Why Decision Transformers Fail in Stochastic Environments](https://arxiv.org/pdf/2205.15967.pdf), 2022.
- [Action-Conditioned Contrastive Policy Pretraining](https://arxiv.org/abs/2204.02393), 2022.
- Multi-agent
- [Offline Pre-trained Multi-Agent Decision Transformer: One Big Sequence Model Tackles All SMAC Tasks](https://arxiv.org/abs/2112.02845), 2021.
- [Multi-Agent Reinforcement Learning is a Sequence Modeling Problem](https://arxiv.org/abs/2205.14953), 2022.
- [Generalized Decision Transformer for Offline Hindsight Information Matching](https://arxiv.org/abs/2111.10364), ICLR 2021 (Spotlight).
- [Prompting Decision Transformer for Few-Shot Policy Generalization](https://arxiv.org/abs/2206.13499), ICML 2022 (Poster).
- [Addressing Optimism Bias in Sequence Modeling for Reinforcement Learning](https://proceedings.mlr.press/v162/villaflor22a.html), ICML 2022 (Poster).
- [RvS: What is Essential for Offline RL via Supervised Learning?](https://arxiv.org/abs/2112.10751), ICLR 2022.

### Offline RL with Online Finetuning
- [Acceleratingonline reinforcement learning with offline datasets](https://arxiv.org/abs/2006.09359), CORR 2022.
- [Offline Reinforcement Learning with Implicit Q-Learning](https://arxiv.org/abs/2110.06169), Arxiv 2021.
- [Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble](https://arxiv.org/abs/2107.00591), CoRL 2021.
- [AW-Opt: Learning Robotic Skills with Imitation and Reinforcement at Scale](https://arxiv.org/abs/2111.05424), CoRL 2021.
- [Online Decision Transformer](https://arxiv.org/abs/2202.05607#facebook), ICML 2022 (Oral).

### Big Models for RL
- ✅ OpenAI VPT [Learning to Play Minecraft with Video PreTraining (VPT)](https://openai.com/blog/vpt/), 2022.
- 用到的Transformer模型:[Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://arxiv.org/abs/1901.02860), 2022.
- NVIDIA MineDojo [MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge](https://arxiv.org/abs/2206.08853), 2022.
- [LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action](https://arxiv.org/abs/2207.04429), 2022.
- [A Dataset Perspective on Offline Reinforcement Learning](https://arxiv.org/abs/2111.04714), 2022.

### Real-World RL
- [Challenges of Real-World Reinforcement Learning](https://arxiv.org/pdf/1904.12901.pdf), 2019.
- [Reinforcement Learning In Practice: Oppotunities And Challenges](https://arxiv.org/pdf/2202.11296.pdf), 2022.

### Autonomous Driving
- [Deep Reinforcement Learning for Autonomous Driving: A Survey](https://arxiv.org/pdf/2002.00444.pdf), 2020.

### Environments
- [DIAMBRA Arena](https://github.com/diambra/arena#diambra-arena): An interface towards popular arcade emulated video games.
- [Bomberland](https://www.gocoder.one/bomberland): A multi-agent AI competition inspired by Bomberman.
- [Honor of Kings Game Environment](https://github.com/tencent-ailab/hok_env): The open environment of Honor of kings 1V1.

### Empirical study
- [What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study](https://arxiv.org/pdf/2006.05990.pdf), 2020.
- [Distilling Policy Distillation](https://arxiv.org/pdf/1902.02186.pdf), 2019.