hongshaorou/Tianshou
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Improve change log #1129

Browse Source
This commit is contained in:
Dominik Jain 2024-04-30 17:47:06 +02:00
parent ea0c4f1a30
commit 393e55aa58
1 changed files with 34 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
CHANGELOG.md
View File

@ -3,16 +3,24 @@
## Release 1.1.0 ## Release 1.1.0
### Api Extensions ### Api Extensions
- Batch received two new methods: `to_dict` and `to_list_of_dicts`. #1063 - `data`:
- `Collector`s can now be closed, and their reset is more granular. #1063 - `Batch`:
- Trainers can control whether collectors should be reset prior to training. #1063 - Add methods `to_dict` and `to_list_of_dicts`. #1063 #1098
- Convenience constructor for `CollectStats` called `with_autogenerated_stats`. #1063 - Add methods `to_numpy_` and `to_torch_`. #1098, #1117
- `SamplingConfig` supports `batch_size=None`. #1077 - Add `__eq__` (semantic equality check). #1098
- Batch received new methods: `to_numpy_` and `to_torch_`. #1098, #1117 - `data.collector`:
- `to_dict` in Batch supports also non-recursive conversion. #1098 - `Collector`:
- Batch `__eq__` implemented, semantic equality check of batches is now possible. #1098 - Add method `close` #1063
- Method `reset` is now more granular (new flags controlling behavior). #1063
- `CollectStats`: Add convenience constructor `with_autogenerated_stats`. #1063
- `trainer`:
- Trainers can now control whether collectors should be reset prior to training. #1063
- `Batch.keys()` deprecated in favor of `Batch.get_keys()` (needed to make iteration consistent with naming) #1105. - `Batch.keys()` deprecated in favor of `Batch.get_keys()` (needed to make iteration consistent with naming) #1105.
- `highlevel.experiment`: - `highlevel`:
- `SamplingConfig`:
- Add support for `batch_size=None`. #1077
- Add `training_seed` for explicit seeding of training and test environments, the `test_seed` is inferred from `training_seed`. #1074
- `highlevel.experiment`:
- `Experiment` now has a `name` attribute, which can be set using `ExperimentBuilder.with_name` and - `Experiment` now has a `name` attribute, which can be set using `ExperimentBuilder.with_name` and
which determines the default run name and therefore the persistence subdirectory. which determines the default run name and therefore the persistence subdirectory.
It can still be overridden in `Experiment.run()`, the new parameter name being `run_name` rather than It can still be overridden in `Experiment.run()`, the new parameter name being `run_name` rather than
@ -22,11 +30,11 @@
- Add method `build_seeded_collection` for the sound creation of multiple - Add method `build_seeded_collection` for the sound creation of multiple
experiments with varying random seeds #1131 experiments with varying random seeds #1131
- Add method `copy` to facilitate the creation of multiple experiments from a single builder #1131 - Add method `copy` to facilitate the creation of multiple experiments from a single builder #1131
- `SamplingConfig` has an explicit training seed, `test_seed` is inferred. #1074 - `evaluation`: New package for repeating the same experiment with multiple seeds and aggregating the results. #1074
- New `evaluation` package for repeating the same experiment with multiple seeds and aggregating the results (important extension!). - The module `evaluation.launchers` for parallelization is currently in alpha state.
Launchers for parallelization currently in alpha state. #1074
- Loggers can now restore the logged data into python by using the new `restore_logged_data` method. #1074 - Loggers can now restore the logged data into python by using the new `restore_logged_data` method. #1074
- `continuous.Critic`: - `utils.net`:
- `continuous.Critic`:
- Add flag `apply_preprocess_net_to_obs_only` to allow the - Add flag `apply_preprocess_net_to_obs_only` to allow the
preprocessing network to be applied to the observations only (without preprocessing network to be applied to the observations only (without
the actions concatenated), which is essential for the case where we want the actions concatenated), which is essential for the case where we want