Eric Liang 5f430da180 [rllib] Provide internal access to episode state in compute_actions() and allow returning extra batches (#2559) ...

The goal of this PR is to allow custom policies to perform model-based rollouts. In the multi-agent setting, this requires access to not only policies of other agents, but also their current observations.
Also, you might want to return the model-based trajectories as part of the rollout for efficiency.

  compute_actions() now takes a new keyword arg episodes
  pull out internal episode class into a top-level file
  add function to return extra trajectories from an episode that will be appended to the sample batch
  documentation

2018-08-16 14:37:21 -07:00

..

benchmarks

[asv] Add benchmark for ray.wait (#2625)

2018-08-10 17:52:36 -07:00

ray

[rllib] Provide internal access to episode state in compute_actions() and allow returning extra batches (#2559)

2018-08-16 14:37:21 -07:00

asv.conf.json

[asv] Pushing to s3 (#2246)

2018-06-20 10:43:44 -07:00

build-wheel-macos.sh

Fix MAC_WHEELS=1 (#2477)

2018-07-25 14:57:28 -07:00

build-wheel-manylinux1.sh

Stop building wheels for Python 3.3 on Linux. (#2342)

2018-07-04 12:22:33 -07:00

README-benchmarks.rst

[rllib][asv] Support ASV for RLlib (#2304)

2018-06-28 17:20:09 -07:00

README-building-wheels.md

[DataFrame] Add Parquet Support in Build Process (#1531)

2018-02-16 07:18:42 -08:00

setup.py

copy all files when installing pyarrow (#2547)

2018-08-02 17:06:37 -07:00