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

..

autoscaler

[autoscaler] Allowing users to provide extra configs for AWS (#7844)

2020-04-04 18:36:51 -07:00

cloudpickle

Python 3.8 compatibility (#7754)

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

core

Define common data structures with protobuf. (#5121)

2019-07-08 22:41:37 +08:00

dashboard

Fix dashboard profiling (#8013)

2020-04-14 08:30:16 -07:00

dataframe

Dataframe deprecation (#2353)

2018-07-06 00:16:22 -07:00

experimental

Cleaning up remaining Local Mode Code (#7865)

2020-04-03 19:54:15 -05:00

includes

[Core] Added ability to specify different IP addresses for a core worker and its raylet. (#7985)

2020-04-16 10:32:24 -05:00

internal

Cleaning up remaining Local Mode Code (#7865)

2020-04-03 19:54:15 -05:00

projects

Fix command config portion of project schema (#8057)

2020-04-16 18:08:17 -07:00

pyarrow_files

Package pyarrow along with ray. (#822)

2017-08-07 21:17:28 -07:00

scripts

Revert "Add ability to specify worker and driver ports (#7833)" (#8069)

2020-04-17 12:32:22 -05:00

serve

Serve Doc: Quickstart (#7940)

2020-04-15 12:25:37 -07:00

tests

Revert "Add ability to specify worker and driver ports (#7833)" (#8069)

2020-04-17 12:32:22 -05:00

tune

[tune] Check actor start -> test_cluster (#8056)

2020-04-16 20:00:45 -07:00

util

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

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

workers

[Core] Added ability to specify different IP addresses for a core worker and its raylet. (#7985)

2020-04-16 10:32:24 -05:00

__init__.py

Remove ray.tasks() from API. (#7807)

2020-04-01 10:10:40 -05:00

_raylet.pxd

Support multiple core workers in one process (#7623)

2020-04-07 11:01:47 +08:00

_raylet.pyx

[Core] Added ability to specify different IP addresses for a core worker and its raylet. (#7985)

2020-04-16 10:32:24 -05:00

actor.py

[serve] Make HTTP proxy fault tolerant (#7936)

2020-04-09 17:07:22 -05:00

async_compat.py

[Serve] Async Router (#6873)

2020-01-30 09:34:47 -08:00

cluster_utils.py

Revert "Add ability to specify worker and driver ports (#7833)" (#8069)

2020-04-17 12:32:22 -05:00

cross_language.py

Remove instances of 'raise Exception' (#7523)

2020-03-10 17:51:22 -07:00

exceptions.py

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

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

function_manager.py

Moving Local Mode to C++ (#7670)

2020-04-01 15:50:57 -05:00

gcs_utils.py

Remove future imports (#6724)

2020-01-09 00:15:48 -08:00

import_thread.py

Remove instances of 'raise Exception' (#7523)

2020-03-10 17:51:22 -07:00

log_monitor.py

Remove future imports (#6724)

2020-01-09 00:15:48 -08:00

memory_monitor.py

First pass at ray memory command for memory debugging (#7589)

2020-03-17 20:45:07 -07:00

monitor.py

Remove ray.tasks() from API. (#7807)

2020-04-01 10:10:40 -05:00

node.py

Revert "Add ability to specify worker and driver ports (#7833)" (#8069)

2020-04-17 12:32:22 -05:00

parameter.py

Revert "Add ability to specify worker and driver ports (#7833)" (#8069)

2020-04-17 12:32:22 -05:00

profiling.py

Remove future imports (#6724)

2020-01-09 00:15:48 -08:00

ray_cluster_perf.py

Move more unit tests to bazel (#6250)

2019-11-24 11:43:34 -08:00

ray_constants.py

Cross language serialization for primitive types (#7711)

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

ray_perf.py

Remove (object) from class declarations. (#6658)

2020-01-02 17:42:13 -08:00

ray_process_reaper.py

Windows bug fixes (#7740)

2020-03-30 20:39:23 -05:00

remote_function.py

Moving Local Mode to C++ (#7670)

2020-04-01 15:50:57 -05:00

reporter.py

Windows bug fixes (#7740)

2020-03-30 20:39:23 -05:00

resource_spec.py

Remove instances of 'raise Exception' (#7523)

2020-03-10 17:51:22 -07:00

rllib

[rllib] Try moving RLlib to top level dir (#5324)

2019-08-05 23:25:49 -07:00

serialization.py

Cross language serialization for primitive types (#7711)

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

services.py

Revert "Add ability to specify worker and driver ports (#7833)" (#8069)

2020-04-17 12:32:22 -05:00

setup-dev.py

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

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

signature.py

Remove dependence on funcsigs. (#7701)

2020-03-22 21:37:24 -07:00

state.py

Remove ray.tasks() from API. (#7807)

2020-04-01 10:10:40 -05:00

streaming

[Streaming] Streaming data transfer and python integration (#6185)

2019-12-10 20:33:24 +08:00

test_utils.py

fix test_worker_stats (#7655)

2020-03-20 14:53:40 +08:00

utils.py

Windows bug fixes (#7740)

2020-03-30 20:39:23 -05:00

worker.py

Minor Ray API doc refinements (#8060)

2020-04-18 15:19:35 -07:00