Tencent / PySC2TencentExtension
☆25Updated 3 years ago
Related projects: ⓘ
- ☆41Updated 3 years ago
- ☆46Updated last year
- ☆70Updated 5 years ago
- ☆18Updated 5 years ago
- A StarCraft 2 agent for harvesting resources☆13Updated 6 years ago
- Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees☆93Updated 5 years ago
- A2C, ACKTR and A2T implementations for ViZDoom☆10Updated 6 years ago
- Source code for the paper "Divergence-Augmented Policy Optimization"☆37Updated 4 years ago
- Fictitious Self-play & Reinforcement Learning☆19Updated 6 years ago
- Reinforcement Learning papers on exploration methods.☆20Updated 3 years ago
- Efficient Reinforcement Learning with a Thought-Game for StarCraft☆46Updated last year
- original source code of the ASE 2019 paper: Wuji: Automatic Online Combat Game Testing Using Evolutionary Deep Reinforcement Learning☆25Updated 4 years ago
- ☆44Updated 5 years ago
- StarCraft AI bot☆62Updated 5 years ago
- Simplified Action Decoder for Deep Multi-Agent Reinforcement Learning☆95Updated 2 years ago
- Code for "Joint Policy Search for Collaborative Multi-agent Incomplete Information Games"☆50Updated 10 months ago
- Distributed implementation of popular evolutionary methods☆63Updated 6 years ago
- ☆30Updated 4 years ago
- Reinforcement Learning and Transfer Learning based StarCraft Micromanagement☆45Updated 6 years ago
- Reinforcement learning algorithms to play Poker☆15Updated 2 years ago
- A platform for intelligent agent learning based on a 3D open-world FPS game developed by Inspir.AI.☆55Updated 2 years ago
- PyDota2 Framework Integrated with DotaService☆25Updated 5 years ago
- ☆36Updated last year
- Tensorflow 2 source code for the PI-SAC agent from "Predictive Information Accelerates Learning in RL" (NeurIPS 2020)☆40Updated last year
- StarCraft 2 Imitation Learning☆29Updated 3 years ago
- ☆20Updated 2 years ago
- Reinforcement Learning Assembly☆92Updated 3 years ago
- Unofficial code for online decision transformer☆37Updated 2 years ago
- A platform of grid world that supports up to 1 million reinforcement-learning agents.☆70Updated 7 years ago
- ☆35Updated this week