wassname/ray
1
0
Fork 0
mirror of https://github.com/wassname/ray.git synced 2026-07-07 13:37:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

[rllib] Update docs with api and components overview figures (#1443)

Browse Source
This commit is contained in:
Eric Liang
2018-01-19 10:08:45 -08:00
committed by Richard Liaw
parent 37076a9ff8
commit e216766bbc
5 changed files with 92 additions and 63 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/ray/rllib/README.rst
+2 -2
View File
@@ -33,8 +33,8 @@ All RLlib algorithms implement a common training API (agent.py), which enables m
# Integration with ray.tune for hyperparam evaluation
python train.py -f tuned_examples/cartpole-grid-search-example.yaml
Evaluator and Optimizer abstractions
------------------------------------
Policy Evaluator and Optimizer abstractions
-------------------------------------------
RLlib's gradient-based algorithms are composed using two abstractions: Evaluators (evaluator.py) and Optimizers (optimizers/optimizer.py). Optimizers encapsulate a particular distributed optimization strategy for RL. Evaluators encapsulate the model graph, and once implemented, any Optimizer may be "plugged in" to any algorithm that implements the Evaluator interface.