A curated list of my interested resources.
- DeepMind AlphaStar, 2019.
- OpenAI Five, 2019.
- Tencent Juewu, 2020.
- Learning Diverse Policies in MOBA Games via Macro-Goals, 2021.
- awesome-game-ai - An awesome library.
- Game AI Pro - Game AI Pro book series.
- GDC Vault - 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, 2021.
- Rethinking of AlphaStar, 2021
- Awesome Human-Centered AI (HCAI) - An awesome library.
- AnyMorph: Learning Transferable Polices By Inferring Agent Morphology, ICML 2022 (Spotlight).
- Related work: One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Control, ICML 2020.
- MetaMorph: Learning Universal Controllers with Transformers, 2022.
- Can Wikipedia Help Offline Reinforcement Learning?, 2022.
- ✅ Decision Transformer: Reinforcement Learning via Sequence Modeling, 2021.
- ✅ Offline Reinforcement Learning as One Big Sequence Modeling Problem, 2021.
- ✅ A Generalist Agent (Gato), 2022.
-> Use prompt conditioning for multi-task. - Online Decision Transformer, ICML 2022 (Oral).
- ✅ Multi-Game Decision Transformers, 2022.
- You Can’t Count on Luck: Why Decision Transformers Fail in Stochastic Environments, 2022.
- Action-Conditioned Contrastive Policy Pretraining, 2022.
- Multi-agent
- Generalized Decision Transformer for Offline Hindsight Information Matching, ICLR 2021 (Spotlight).
- Prompting Decision Transformer for Few-Shot Policy Generalization, ICML 2022 (Poster).
- Addressing Optimism Bias in Sequence Modeling for Reinforcement Learning, ICML 2022 (Poster).
- RvS: What is Essential for Offline RL via Supervised Learning?, ICLR 2022.
- Acceleratingonline reinforcement learning with offline datasets, CORR 2022.
- Offline Reinforcement Learning with Implicit Q-Learning, Arxiv 2021.
- Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble, CoRL 2021.
- AW-Opt: Learning Robotic Skills with Imitation and Reinforcement at Scale, CoRL 2021.
- Online Decision Transformer, ICML 2022 (Oral).
- ✅ OpenAI VPT Learning to Play Minecraft with Video PreTraining (VPT), 2022.
- 用到的Transformer模型:Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context, 2022.
- NVIDIA MineDojo MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge, 2022.
- LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action, 2022.
- A Dataset Perspective on Offline Reinforcement Learning, 2022.
- Challenges of Real-World Reinforcement Learning, 2019.
- Reinforcement Learning In Practice: Oppotunities And Challenges, 2022.
- DIAMBRA Arena: An interface towards popular arcade emulated video games.
- Bomberland: A multi-agent AI competition inspired by Bomberman.
- Honor of Kings Game Environment: The open environment of Honor of kings 1V1.