nicoguertler / graph_rl
Hierarchical reinforcement learning framework which uses a directed graph to define the hierarchy.
☆12Updated 2 years ago
Alternatives and similar repositories for graph_rl:
Users that are interested in graph_rl are comparing it to the libraries listed below
- The code for AAMAS2022 《GCS: Graph-based Coordination Strategy for Multi-Agent Reinforcement Learning》☆41Updated 3 years ago
- Implementation for mSAC methods in PyTorch☆41Updated 3 years ago
- ☆11Updated 10 months ago
- (ICML 2023) The official code for RACE: Improve Multi-Agent Reinforcement Learning with Representation Asymmetry and Collaborative Evolut…☆34Updated last year
- ☆39Updated 2 years ago
- Code for "ALMA: Hierarchical Learning for Composite Multi-Agent Tasks" NeurIPS 2022☆28Updated 2 years ago
- A Pytorch Implementation of Multi Agent Soft Actor Critic☆40Updated 6 years ago
- Hierarchical Cooperative Multi-Agent Reinforcement Learning with Skill Discovery☆102Updated 2 years ago
- Implementation of centralized training, centralized execution of Soft Actor-Critic (SAC) on a Tennis multiagent Unity environment.☆35Updated 4 years ago
- The official code releasement of publications in MARL field of TJU RL lab.☆74Updated 2 years ago
- qmix☆22Updated 4 years ago
- Implementation code for GraphMIX: Graph Convolutional Value Decomposition in Multi-Agent Reinforcement Learning☆32Updated 4 years ago
- Implementation of DyMA-CL, MARL algorithm☆27Updated 5 years ago
- Multi-agent PPO with noise (97% win rates on Hard scenarios of SMAC)☆61Updated last year
- PyTorch Implementation of FeUdal Networks for Hierarchical Reinforcement Learning (FuNs), Vezhnevets et al. 2017.☆39Updated 4 years ago
- Value-Decomposition Multi-Agent Actor-Critics☆40Updated 2 years ago
- Communication using GNN in MARL☆20Updated 3 years ago
- A collection of Meta-Reinforcement Learning algorithms in PyTorch☆41Updated 9 months ago
- Bayesian Soft Actor Critic☆14Updated 2 years ago
- ☆40Updated 3 years ago
- ICML 2019 RL for Real Life Workshop: Recurrent MADDPG for Partially Observable and Limited Communication Settings☆48Updated 5 years ago
- RLToolkit is a flexible and high-efficient reinforcement learning framework. Include implementation of DQN, AC, ACER, A2C, A3C, PG, DDPG,…☆17Updated last year
- Codes for the paper "HAVEN: Hierarchical Cooperative Multi-Agent Reinforcement Learning with Dual Coordination Mechanism"☆22Updated 2 years ago
- Code for our paper: Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation☆108Updated 3 months ago
- Hybrid action space reinforcement learning algorithms.☆12Updated 4 years ago
- The code of paper "Learning Heterogeneous Strategies via Graph-based Multi-agent Reinforcement Learning in Mixed Cooperative-Competitive …☆14Updated 3 years ago
- Implementation of the Discrete Soft Actor-Critic algorithm with RNN policy in PyTorch☆26Updated 2 years ago
- Source code for paper: An Efficient Transfer Learning Framework for Multiagent Reinforcement Learning☆23Updated 2 years ago
- Implementations of MAPPO and IPPO on SMAC, the multi-agent StarCraft environment.☆65Updated 3 years ago
- reinforcement learning with pytorch geometric library☆48Updated 3 years ago