Learning with Opponent-Learning Awareness

  title={Learning with Opponent-Learning Awareness},
  author={Jakob N. Foerster and Richard Y. Chen and Maruan Al-Shedivat and Shimon Whiteson and Pieter Abbeel and Igor Mordatch},
Multi-agent settings are quickly gathering importance in machine learning. This includes a plethora of recent work on deep multiagent reinforcement learning, but also can be extended to hierarchical reinforcement learning, generative adversarial networks and decentralised optimization. In all these settings the presence of multiple learning agents renders the training problem non-stationary and often leads to unstable training or undesired final results. We present Learning with Opponent… CONTINUE READING


Publications citing this paper.


Publications referenced by this paper.
Showing 1-10 of 47 references

The Application of Decision Theory and Dynamic Programming to Adaptive Control Systems

  • King Lee, K Louis
  • Ph.D. Dissertation
  • 1967
Highly Influential
16 Excerpts

Similar Papers

Loading similar papers…