wassname/ray
1
0
Fork 0
mirror of https://github.com/wassname/ray.git synced 2026-09-12 12:51:15 +08:00
Code Issues Packages Projects Releases Wiki Activity

[rllib] Support agent.get_action in multiagent (#2543)

Browse Source 
* support get action on policy id

* comment

* grammar fixes

* Update rllib-algorithms.rst
This commit is contained in:
Eric Liang
2018-08-02 13:35:53 -07:00
committed by GitHub
parent d2ebe4d9a3
commit f7ec292360
3 changed files with 54 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
doc/source/rllib-algorithms.rst
+2 -2
View File
@@ -59,7 +59,7 @@ Tuned examples: `PongNoFrameskip-v4 <https://github.com/ray-project/ray/blob/mas
.. figure:: impala.png
:align: center
RLlib's IMPALA implementation scales from 16 to 128 workers on PongNoFrameskip-v4. With vectorization, similar learning performance to 128 workers can be achieved with only 32 workers. This about an order of magnitude faster than A3C, with similar sample efficiency.
RLlib's IMPALA implementation scales from 16 to 128 workers on PongNoFrameskip-v4. With vectorization, similar learning performance to 128 workers can be achieved with only 32 workers. This is about an order of magnitude faster than A3C (not shown here), with similar sample efficiency.
Policy Gradients
----------------
@@ -78,4 +78,4 @@ Tuned examples: `Humanoid-v1 <https://github.com/ray-project/ray/blob/master/pyt
:width: 500px
:align: center
RLlib's multi-GPU PPO can scale to hundreds of cores and be more cost effective than MPI-based implementations by leveraging mixed GPU and high-CPU machines.
RLlib's multi-GPU PPO scales to multiple GPUs and hundreds of CPUs. Here we compare against a reference MPI-based implementation.