Sven Mika 165a86f1ab [RLlib] SAC MuJoCo instability issues (tf and torch versions). (#8063) ...

SAC (both torch and tf versions) are showing issues (crashes) due to numeric instabilities in the SquashedGaussian distribution (sampling + logp after extreme NN outputs).
This PR fixes these. Stable MuJoCo learning (HalfCheetah) has been confirmed on both tf and torch versions. A Distribution stability test (using extreme NN outputs) has been added for SquashedGaussian (can be used for any other type of distribution as well).

2020-04-19 10:20:23 +02:00

..

ray

[RLlib] SAC MuJoCo instability issues (tf and torch versions). (#8063)

2020-04-19 10:20:23 +02:00

asv.conf.json

Replace all instances of ray.readthedocs.io with ray.io (#7994)

2020-04-13 16:17:05 -07:00

build-wheel-macos.sh

Python 3.8 compatibility (#7754)

2020-04-01 10:03:23 -07:00

build-wheel-manylinux1.sh

Python 3.8 compatibility (#7754)

2020-04-01 10:03:23 -07:00

MANIFEST.in

[autoscaler] Replace cluster yaml validation with json schema v… (#7261)

2020-03-10 18:58:55 -07:00

README-building-wheels.md

fix wheel building doc (#4360)

2019-03-13 23:11:30 -07:00

setup.py

Cross language serialization for primitive types (#7711)

2020-04-08 21:10:57 +08:00