Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Fine-tuned MARL algorithms on SMAC (100% win rates on most scenarios)
| Date | Stars |
|---|---|
| 2026-07-31 | 709 |
| 2026-08-03 | 709 |
| 2026-08-06 | 709 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
```diff - If you want high sample efficiency, please use qmix_high_sample_efficiency.yaml - which uses 4 processes for training, slower but higher sample efficiency. - Performance is *not* comparable of models trained with different number of processes. ``` # PyMARL2 Open-source code for [Rethinking the Implementation Tricks and Monotonicity Constraint in Cooperative Multi-Agent Reinforcement Learning](https://arxiv.org/abs/2102.03479). This repository is fine-tuned for StarCraft Multi-agent Challenge (SMAC). For other multi-agent tasks, we also recommend an optimized implementation of QMIX: https://github.com/marlbenchmark/off-policy. **StarCraft 2 version: SC2.4.10. difficulty: 7.** ``` 2022.10.10 update: add qmix_high_sample_efficiency.yaml, which uses 4 processes for training, slower but higher sample efficiency. 2021.10.28 update: add Google Football Environments [vdn_gfootball.yaml] (use `simple115 features`). 2021.10.4 update: add QMIX with attention (qmix_att.yaml) as a baseline for Communication tasks. ``` ## Finetuned-QMIX There are so many code-level tricks in the Multi-agent Reinforcement Learning (MARL), such as: - Value function clipping (clip max Q values for QMIX) - Value Normalization - Reward scaling - Orthogonal initialization and layer scaling - **Adam** - **Neural networks hidden size** - learning rate annealing - Reward Clipping - Observation Normalization - Gradient Clipping - **Large Batch Size** - **N-step Returns(including GAE($\lambda$) and Q($\lambda$) ...)** - **Rollout Process Number** - **$\epsilon$-greedy annealing steps** - Death Agent Masking **Related Works** - Implementation Matters in Deep RL: A Case Study on PPO and TRPO - What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study - The Surprising Effectiveness of MAPPO in Cooperative, Multi-Agent Games Using a few of tricks above (bold texts), we enabled QMIX (qmix.yaml) to solve almost all hard scenarios of SMAC (Fine-tuned hyperparameters **for each scenarios**). | Senarios | Difficulty | QMIX (batch_size=128) | Finetuned-QMIX | | ------------ | :--------: | :-------------------: | :------------------------------------------------: | | 8m | Easy | - | **100\%** | | 2c_vs_1sc | Easy | - | **100\%** | | 2s3z | Easy | - | **100\%** | | 1c3s5z | Easy | - | **100\%** | | 3s5z | Easy | - | **100\%** | | 8m_vs_9m | Hard | 84% | **100\%** | | 5m_vs_6m | Hard | 84% | **90\%** | | 3s_vs_5z | Hard | 96% | **100\%** | | bane_vs_bane | Hard | **100\%** | **100\%** | | 2c_vs_64zg | Hard | **100\%** | **100\%** | | corridor | Super Hard | 0% | **100\%** | | MMM2 | Super Hard | 98% | **100\%** | | 3s5z_vs_3s6z | Super Hard | 3% | **93\%**(hidden_size = 256, qmix_large.yaml) | | 27m_vs_30m | Super Hard | 56% | **100\%** | | 6h_vs_8z | Super Hard | 0% | **93\%**($\lambda$ = 0.3, epsilon_anneal_time = 500000) | ## Re-Evaluation Afterwards, we re-evaluate numerous QMIX variants with normalized the tricks (a **general** set of hyperparameters), and find that QMIX achieves the SOTA. | Scenarios | Difficulty | Value-based | |
Excerpt of 11,288 characters
Read on GitHub
152
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:b03042323cc77ad1, topic:reinforcement-learning