dev/openfuyao-2.48.0

文件	最后提交记录	最后更新时间
doc_code	[Doc] Various improvements to the Getting Started page (#50878) ## Why are these changes needed? - adds links to Slack and Discourse - add clearer introduction to each library and improved overall readability - add missing dependency install instructions - updated rllib example to use latest API - polished the rllib example code - make Vale happy ## Related issue number NA ## Checks - [x] I've signed off every commit(by using the -s flag, i.e., git commit -s) in this PR. - [x] I've run scripts/format.sh to lint the changes in this PR. - [ ] I've included any doc changes needed for https://docs.ray.io/en/master/. - [ ] I've added any new APIs to the API Reference. For example, if I added a method in Tune, I've added it in doc/source/tune/api/ under the corresponding .rst file. - [ ] I've made sure the tests are passing. Note that there might be a few flaky tests, see the recent failures at https://flakey-tests.ray.io/ - Testing Strategy - [ ] Unit tests - [ ] Release tests - [ ] This PR is not tested :( --------- Signed-off-by: Ricardo Decal <rdecal@anyscale.com> Signed-off-by: Ricardo Decal <crypdick@users.noreply.github.com> Signed-off-by: Philipp Moritz <pcmoritz@gmail.com> Co-authored-by: angelinalg <122562471+angelinalg@users.noreply.github.com> Co-authored-by: Philipp Moritz <pcmoritz@gmail.com>	1 年前
images	[RLlib] Docs do-over (new API stack): Remove rllib-models.rst. (#49966)	1 年前
package_ref	[RLlib] Enable merging of Stats per index of values (#52897) ## Why are these changes needed? Today, when merging stats in parallel, when reducing n Stats, the first n merged values will be the reduced values of all incoming values at index 0, the next n merged values will be the reduced values of all incoming values at index 1, etc. This is fine most of the time, but alternatively, we can reduce incoming values per index such that the new value at index n will be the reduced value of all incoming values at index n. This PR introduces a new flag for Stats to switch between the two behaviours. It also adds significant test coverage for different combinations of Stats parameters. With this PR, I also hope to make the API a bit crisper in terms of clear separation of concerns for MetricsLogger logging vs aggregation methods.	1 年前
algorithm-config.rst	[RLlib; docs] Docs do-over (new API stack): Rewrite/enhance "getting started" rst page. (#49950)	1 年前
checkpoints.rst	[RLlib] Examples folder do-over (vol 52): Move ONNX examples (plain and w/ LSTM) from old- to new API stack. (#52969)	1 年前
external-envs.rst	[RLlib; docs] Docs do-over (new API stack): Rewrite/enhance "getting started" rst page. (#49950)	1 年前
getting-started.rst	[RLlib; docs] Docs do-over (new API stack): Rewrite/enhance "getting started" rst page. (#49950)	1 年前
hierarchical-envs.rst	[RLlib; docs] Docs do-over (new API stack): Move "new API stack" info box right below page titles for better visibility. (#49921)	1 年前
index.rst	[RLlib; docs] Fix some broken html links. (#50126)	1 年前
key-concepts.rst	[RLlib] APPO accelerate (vol 17): LearnerGroup should not pickle remote functions on each update-call; Refactor LearnerGroup and Learner APIs. (#50665)	1 年前
metrics-logger.rst	[RLlib] MetricsLogger + Stats overhaul. (#51639)	1 年前
multi-agent-envs.rst	[RLlib; docs] Docs do-over (new API stack): Rewrite/enhance "getting started" rst page. (#49950)	1 年前
new-api-stack-migration-guide.rst	[RLlib; docs] Fix some broken html links. (#50126)	1 年前
rl-modules.rst	[RLlib] Examples folder do-over (vol 52): Custom action distribution example (new script, replaces existing Catalogs-based one). (#53262)	1 年前
rllib-advanced-api.rst	[RLlib; docs] Fix some broken html links. (#50126)	1 年前
rllib-algorithms.rst	[RLlib; docs] Fix 4 broken html links. (#51015)	1 年前
rllib-callback.rst	[RLlib] Episode API: Add custom_data property and deprecate add|get_temporary_timestep_data() APIs. (#52603)	1 年前
rllib-dev.rst	[RLlib; docs] Docs do-over (new API stack): Remove special "new API stack" page (move some of its content to migration guide). (#49713)	1 年前
rllib-env.rst	[RLlib; docs] Fix 4 broken html links. (#51015)	1 年前
rllib-examples.rst	[RLlib] Enhance ConnectorV2 ObservationPreprocessor APIs (add multi-agent support; add episode arg). (#54209)	1 年前
rllib-fault-tolerance.rst	Fix lint (#49746) Signed-off-by: dentiny <dentinyhao@gmail.com>	1 年前
rllib-learner.rst	[RLlib] APPO accelerate (vol 17): LearnerGroup should not pickle remote functions on each update-call; Refactor LearnerGroup and Learner APIs. (#50665)	1 年前
rllib-offline.rst	Fix typos (#53048) Signed-off-by: omahs <73983677+omahs@users.noreply.github.com>	1 年前
rllib-replay-buffers.rst	Fix typos in doc directory (#51054) Signed-off-by: co63oc <co63oc@users.noreply.github.com>	1 年前
rllib-torch2x.rst	[RLlib] Docs do-over (new API stack): Remove rllib-models.rst. (#49966)	1 年前
scaling-guide.rst	[RLlib; docs] Fix some broken html links. (#50126)	1 年前
single-agent-episode.rst	[RLlib; docs] Docs do-over (new API stack): Move "new API stack" info box right below page titles for better visibility. (#49921)	1 年前
user-guides.rst	[RLlib] Docs do-over (new API stack): Remove rllib-models.rst. (#49966)	1 年前