Multi-agent reinforcement learning
Reward Shaping for Cooperative Multi-Agent Locomotion
A study of how reward shaping affects convergence and coordination in cooperative multi-agent locomotion.
- Year
- 2024
- Status
- Project
- Topics
- Multi-agent RL · Reward design · Coordination
A conceptual illustration of the mathematical idea, not a plot of measured experimental results.
The question
Which reward signals teach independent agents to coordinate without destabilizing learning?
Central insight
A team reward expresses the final goal but can provide weak credit assignment. Shaped local signals can help, yet may create strategies that optimize the proxy instead of the task.
Approach
- 01
Design reward formulations for cooperative locomotion.
- 02
Train multi-agent policies using the proposed rewards.
- 03
Benchmark the effect on convergence and coordination.
My contribution
- Designed reward shaping for cooperative multi-agent reinforcement learning.
- Benchmarked its effect on convergence and coordination.
Result
The evaluation examines how changing the reward affects learning behavior and coordination between agents.
What remains
A possible next investigation is how consistently the coordination behavior appears across independent training runs.