2c1acda2f3
- Update DQN trainer with gradient collapse detection warmup - Add portfolio tracker improvements - Include hyperopt trial results (multiple Sharpe ratio experiments) - Add new test files for action/position sign convention, early stopping, cash reserve bugs, and portfolio execution - Update trained model files - Add Claude Code configuration and skills 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
29 lines
545 B
Markdown
29 lines
545 B
Markdown
# agent-coordination
|
|
|
|
Coordination patterns for multi-agent collaboration.
|
|
|
|
## Coordination Patterns
|
|
|
|
### Hierarchical
|
|
Queen-led with worker specialization
|
|
```bash
|
|
npx claude-flow swarm init --topology hierarchical
|
|
```
|
|
|
|
### Mesh
|
|
Peer-to-peer collaboration
|
|
```bash
|
|
npx claude-flow swarm init --topology mesh
|
|
```
|
|
|
|
### Adaptive
|
|
Dynamic topology based on workload
|
|
```bash
|
|
npx claude-flow swarm init --topology adaptive
|
|
```
|
|
|
|
## Best Practices
|
|
- Use hierarchical for complex projects
|
|
- Use mesh for research tasks
|
|
- Use adaptive for unknown workloads
|