quantumiracle / nash-dqn
Official code of Nash-DQN for paper: Nash-DQN algorithm for two-player zero-sum Markov games, details see our paper: A Deep Reinforcement Learning Approach for Finding Non-Exploitable Strategies in Two-Player Atari Games. Zihan Ding, Dijia Su, Qinghua Liu, Chi Jin
☆17Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for nash-dqn
- MARS is shortened for Multi-Agent Research Studio, a library for mulit-agent reinforcement learning research.☆44Updated 8 months ago
- The official repository of Decoupled Reinforcement Learning to Stabilise Intrinsically-Motivated Exploration" (AAMAS 2022)☆26Updated 2 years ago
- Code for NeurIPS2023 accepted paper: Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning.☆25Updated 4 months ago
- ☆71Updated 5 months ago
- PyTorch Implementation of FeUdal Networks for Hierarchical Reinforcement Learning (FuNs), Vezhnevets et al. 2017.☆36Updated 4 years ago
- When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment, NeurIPS 2023 (oral)☆52Updated 9 months ago
- Official codebase for paper "Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learning" (ICML22)☆21Updated 2 years ago
- DecentralizedLearning☆21Updated last year
- ☆28Updated 3 years ago
- Deep Implicit Coordination Graphs☆41Updated 5 months ago
- Learning Task Embeddings for Teamwork Adaptation in Multi-Agent Reinforcement Learning☆11Updated 6 months ago
- Codebase for [Order Matters: Agent-by-agent Policy Optimization](https://openreview.net/forum?id=Q-neeWNVv1)☆26Updated last year
- ☆18Updated last year
- The implementation of ICLR-2023 paper "Discovering Generalizable Multi-agent Coordination Skills from Multi-task Offline Data".☆37Updated last week
- 🔥 Datasets and env wrappers for offline safe reinforcement learning☆73Updated last month
- Safe Multi-Agent MuJoCo benchmark for safe multi-agent reinforcement learning research.☆50Updated 4 months ago
- ☆45Updated 3 years ago
- ☆14Updated 2 years ago
- Codes accompanying the paper "DOP: Off-Policy Multi-Agent Decomposed Policy Gradients" (ICLR 2021, https://arxiv.org/abs/2007.12322)☆52Updated last year
- Implementation of Tactical Optimistic and Pessimistic value estimation☆25Updated last year
- Policy Expansion for Bridging Offline-to-Online Reinforcement Learning (ICLR23)☆47Updated last year
- Code for Towards Unifying Behavioral and Response Diversity for Open-ended Learning in Zero-sum Games☆19Updated 2 years ago
- ☆18Updated 3 years ago
- We investigate the effect of populations on finding good solutions to the robust MDP☆28Updated 3 years ago
- Cooperative Multi-goal Multi-stage Multi-agent Reinforcement Learning☆55Updated 2 years ago
- Learning Individual Intrinsic Reward in MARL☆62Updated last year
- Related papers for offline reforcement learning (we mainly focus on representation and sequence modeling and conventional offline RL)☆17Updated 2 years ago
- The Starcraft Multi-Agent challenge lite☆35Updated last month
- Distributional Soft Actor Critic☆49Updated 4 years ago
- Official Implementation for Quality-Similar Diversity via Population Based Reinforcement Learning☆17Updated last year