MADDPG implementation in RLlib (#5348)

doc/source/rllib-algorithms.rst

@@ -300,6 +300,19 @@ Tuned examples: `Two-step game <https://github.com/ray-project/ray/blob/master/r
    :start-after: __sphinx_doc_begin__
    :end-before: __sphinx_doc_end__
 
+Multi-Agent Actor Critic (contrib/MADDPG)
+-----------------------------------------
+`[paper] <https://arxiv.org/abs/1706.02275>`__ `[implementation] <https://github.com/ray-project/ray/blob/master/rllib/contrib/maddpg/maddpg.py>`__ MADDPG is a specialized multi-agent algorithm. Code here is adapted from https://github.com/openai/maddpg to integrate with RLlib multi-agent APIs. Please check `wsjeon/maddpg-rllib <https://github.com/wsjeon/maddpg-rllib>`__ for examples and more information.
+
+**MADDPG-specific configs** (see also `common configs <rllib-training.html#common-parameters>`__):
+
+Tuned examples: `Multi-Agent Particle Environment <https://github.com/wsjeon/maddpg-rllib/tree/master/plots>`__, `Two-step game <https://github.com/ray-project/ray/blob/master/rllib/examples/twostep_game.py>`__
+
+.. literalinclude:: ../../rllib/contrib/maddpg/maddpg.py
+   :language: python
+   :start-after: __sphinx_doc_begin__
+   :end-before: __sphinx_doc_end__
+
 Advantage Re-Weighted Imitation Learning (MARWIL)
 -------------------------------------------------
 

doc/source/rllib.rst

@@ -84,6 +84,7 @@ Algorithms
 *  Multi-agent specific
 
    -  `QMIX Monotonic Value Factorisation (QMIX, VDN, IQN) <rllib-algorithms.html#qmix-monotonic-value-factorisation-qmix-vdn-iqn>`__
+   -  `Multi-Agent Actor Critic (contrib/MADDPG) <rllib-algorithms.html#multi-agent-actor-critic-contrib-maddpg>`__
 
 *  Offline