WORK IN PROGRESS
- Implementation of algorithm presented in OpenAI's publication "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments" (Lowe et al., https://arxiv.org/pdf/1706.02275.pdf)
- Does not include "Inferring policies of other agents" and "policy ensembles"
- multiagent-particle-environment: follow install instructions in https://github.com/openai/multiagent-particle-envs
- Tested on Spread environment.
- TODO:
- Test on competitive tasks
- Python 3.6
- PyTorch 0.4.1
- multiagent-particle-environment: follow install instructions in https://github.com/openai/multiagent-particle-envs