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

Commit Graph

  • dffe8cddf6 fix pandas dependency Maximilian Huettenrauch 2024-03-26 14:40:08 +01:00
  • 5a3f2291c2 added pandas dependency Maximilian Huettenrauch 2024-03-26 14:37:43 +01:00
  • 85204b175c added matplotlib dependency Maximilian Huettenrauch 2024-03-26 14:32:42 +01:00
  • 2e3f0b5e99 move doc string Maximilian Huettenrauch 2024-03-26 14:26:27 +01:00
  • d9a201754c updates Maximilian Huettenrauch 2024-03-26 14:23:54 +01:00
  • 516c956d58 Merge branch 'thuml_master' into feature/algo-eval Maximilian Huettenrauch 2024-03-25 10:32:42 +01:00
  • 61bf9adaff
         Update CHANGELOG.md [skip ci] Michael Panchenko 2024-03-20 23:09:26 +01:00
  • 5f96a57bbb
         Add CHANGELOG.md Michael Panchenko 2024-03-20 23:08:34 +01:00
  • 1a4d7deca6
         Update publish.yaml, typo [skip ci[ v1.0.0 Michael Panchenko 2024-03-20 00:41:46 +01:00
  • 72df9a580d
         Update publish.yaml [skip ci] Michael Panchenko 2024-03-20 00:41:17 +01:00
  • 55e9bee373
         Update publish.yaml [skip ci] Michael Panchenko 2024-03-20 00:39:54 +01:00
  • e3661c11e3
         Update publish.yaml, missing / [skip ci] Michael Panchenko 2024-03-20 00:26:11 +01:00
  • 5259d5f3fb Merge branch 'thuml_master' into feature/algo-eval Maximilian Huettenrauch 2024-03-15 09:42:17 +01:00
  • e82379c47f
         Allow explicit setting of multiprocessing context for SubprocEnvWorker (#1072) maxhuettenrauch 2024-03-14 11:07:56 +01:00
  • a7898b15b8 small fix Maximilian Huettenrauch 2024-03-12 15:17:33 +01:00
  • d9a612a997 format, type check and small fixes Maximilian Huettenrauch 2024-03-12 15:01:50 +01:00
  • f730782f29 Merge branch 'thuml_master' into feature/algo-eval Maximilian Huettenrauch 2024-03-12 11:46:08 +01:00
  • 6c1bd85521 add mujoco example with multiple runs and performance plots Maximilian Huettenrauch 2024-03-12 11:44:48 +01:00
  • 5762d2c2e0 extend hl experiment builder Maximilian Huettenrauch 2024-03-12 11:43:52 +01:00
  • 734119ec00 logger updates Maximilian Huettenrauch 2024-03-12 11:31:41 +01:00
  • 32cd3b4357 logger updates - introduced logger manager - loggers can reload logged data from disk Maximilian Huettenrauch 2024-03-11 10:29:17 +01:00
  • 1714c7f2c7
         High-level API: Fix number of test episodes being incorrectly scaled by number of envs (#1071) Dominik Jain 2024-03-07 17:57:11 +01:00
  • 95cbfe6cdf added explicit env seeding for train and test envs Maximilian Huettenrauch 2024-03-06 17:09:06 +01:00
  • 6746a80f6d
         Add publish workflow, first preparation for next release (#1067) Michael Panchenko 2024-03-04 12:21:49 +01:00
  • fdb69f1273
         Improve README, minor changes in procedural example (#1068) Michael Panchenko 2024-03-03 15:07:07 +01:00
  • b6b2c95ac7 Improve README, minor changes in procedural example Dominik Jain 2024-03-02 13:17:15 +01:00
  • 1aee41fa9c
         Using dist.mode instead of logits.argmax (#1066) Erni 2024-03-03 00:09:39 +01:00
  • 7c970df53f
         Fix/add watch env with obs rms (#1061) maxhuettenrauch 2024-02-29 15:59:11 +01:00
  • 49781e715e
         Fix high-level examples (#1060) Dominik Jain 2024-02-23 23:17:14 +01:00
  • 0b61bf8caf
         Fix the link to the contributing guide. (#1062) Ashok Arora 2024-02-24 03:45:41 +05:30
  • ce371ae736
         remove old python versions from poetry classifier (#1059) Carlo Cagnetta 2024-02-21 15:27:53 +01:00
  • 9b6cb6903e
         Improvements in High-Level API and Poe Tasks (#1055) Michael Panchenko 2024-02-15 12:02:16 +01:00
  • 26e210a6ae Apply nbqa only to the docs/ folder and exclude the (old) jupyter_execute folder Dominik Jain 2024-02-15 11:38:23 +01:00
  • 08728ad35e Resolve platform-specific/installation-specific mypy issues by adding ignores and ignoring unused ignores locally Dominik Jain 2024-02-15 11:26:54 +01:00
  • f2e0fd165d Fix gitignore applying to tianshou/env on platfoms with case-insensitive file system Dominik Jain 2024-02-15 11:26:39 +01:00
  • eeb2081ca6 Fix AutoAlphaFactoryDefault using hard-coded Adam optimizer instead of passed factory Dominik Jain 2024-02-14 20:43:38 +01:00
  • 76cbd7efc2 Make OptimizerFactory more flexible by adding a second method which allows the creation of an optimizer given arbitrary parameters (rather than a module) Dominik Jain 2024-02-14 20:42:06 +01:00
  • bf391853dc Allow to configure number of test episodes in high-level API Dominik Jain 2024-02-14 19:06:01 +01:00
  • 8742e3645c
         Docs, js - typo in path Michael Panchenko 2024-02-14 10:50:06 +01:00
  • 5cc51145da
         Docs/hotfix (#1052) Michael Panchenko 2024-02-12 18:54:38 +01:00
  • 7a30b842b6
         Add vega scripts explictly to config (#1051) Michael Panchenko 2024-02-12 18:49:32 +01:00
  • d3fe87b70d
         Docs: added symlinks for paths resolution, removed jquery loading (#1050) Michael Panchenko 2024-02-12 17:38:25 +01:00
  • e3c610d37c
         Docs: Added jquery, better handling of js files through sphinx config… (#1049) Michael Panchenko 2024-02-12 15:43:32 +01:00
  • 33d241a29b
         Docs/html doc issues (#1048) Michael Panchenko 2024-02-09 19:43:10 +01:00
  • 5fc314bd4b
         Docs/use nbqa on notebooks (#1041) Carlo Cagnetta 2024-02-07 17:28:16 +01:00
  • 5fe9aea798
         Update and fix dependencies related to mac install (#1044) maxhuettenrauch 2024-02-06 17:06:38 +01:00
  • eb0215cf76
         Refactoring/mypy issues test (#1017) Daniel Plop 2024-02-06 14:24:30 +01:00
  • 4756ee80ff
         Fixed links and added poetry install info in README [skip ci] Michael Panchenko 2024-01-24 18:07:02 +01:00
  • a0e0824c64
         Typo in README.md [skip ci] Michael Panchenko 2024-01-24 17:50:15 +01:00
  • 69a0e6bbd7
         Bump notebook from 7.0.6 to 7.0.7 (#1027) dependabot[bot] 2024-01-23 19:48:58 +01:00
  • 6577cfa01e
         Bump pillow from 10.0.1 to 10.2.0 (#1030) dependabot[bot] 2024-01-23 19:48:43 +01:00
  • b5ed0c4c67
         Bump jupyterlab from 4.0.9 to 4.0.11 (#1028) dependabot[bot] 2024-01-23 19:48:31 +01:00
  • 7f31294bfd
         Bump jupyter-lsp from 2.2.0 to 2.2.2 (#1026) dependabot[bot] 2024-01-23 19:48:15 +01:00
  • 6e1ffe58e5
         Improvements in README and high-level API (#1022) Michael Panchenko 2024-01-16 15:24:41 +01:00
  • 022cfb7f78 Cleaned up handling of output_dim retrieval, adding exceptions for erroneous cases Dominik Jain 2024-01-16 13:25:41 +01:00
  • 20074931d5 Improve docstrings Dominik Jain 2024-01-16 12:34:48 +01:00
  • 05a8cf4e74 Refactoring, improving class name EnvFactoryGymnasium -> EnvFactoryRegistered Dominik Jain 2024-01-16 12:22:07 +01:00
  • c9cb41bf55 Make envpool usage configuration more explicit Dominik Jain 2024-01-16 12:16:46 +01:00
  • a4d7ccba26 Remove PyTorch warning from README Dominik Jain 2024-01-12 16:59:00 +01:00
  • be9eb7e241 Improve language in README Dominik Jain 2024-01-12 16:58:35 +01:00
  • 3c564e82b7 Remove video from procedural example as it pertains to a different algorithm Dominik Jain 2024-01-12 15:33:33 +01:00
  • 2c72171fca Update procedural example in README Dominik Jain 2024-01-12 13:47:12 +01:00
  • 62d58faa02 Add example from README (with minor updates) Dominik Jain 2024-01-12 13:36:08 +01:00
  • 39f3ba2266 Add screen recording of high-level example Dominik Jain 2024-01-12 13:18:19 +01:00
  • 961e9a7801 Add high-level example to README Dominik Jain 2024-01-11 18:12:22 +01:00
  • cb8e029def
         Bump jinja2 from 3.1.2 to 3.1.3 (#1021) dependabot[bot] 2024-01-12 11:03:12 -08:00
  • 8d6df2b276 Add high-level discrete example (CartPole) for README Dominik Jain 2024-01-08 18:12:43 +01:00
  • 1e5ebc2a2d Improve naming of callback classes and related methods/attributes Dominik Jain 2024-01-10 15:28:48 +01:00
  • 24b7b82e56 Remove inappropriate warning (warns about supported case according to docstring) Dominik Jain 2024-01-11 17:08:54 +01:00
  • ff398beed9 Move callbacks for setting DQN epsilon values to the library Dominik Jain 2024-01-11 14:57:03 +01:00
  • 63269fe198 Implement make_atari_env via AtariEnvFactory, eliminating duplication Dominik Jain 2024-01-11 12:43:05 +01:00
  • 19a98c3b2a Fix models using scale_obs not being persistable (due to locally defined class) Dominik Jain 2024-01-11 12:34:26 +01:00
  • 7fa588309b Update MuJoCo examples to use Ant-v4 instead of Ant-v3 Dominik Jain 2024-01-10 15:39:53 +01:00
  • eaab7b0a4b Improve environment factory abstractions in high-level API: Dominik Jain 2024-01-10 15:37:58 +01:00
  • 94665ac77f
         Bump gitpython from 3.1.40 to 3.1.41 (#1020) dependabot[bot] 2024-01-10 14:22:54 -08:00
  • 8188a904af Reintroduce ignored Ruff rules D106 and D205 Dominik Jain 2024-01-10 15:23:54 +01:00
  • d4e4f4ff63 Experiment builders for DQN and IQN: * Fix: Disable softmax in default models * Add method with_model_factory_default (for DQN) Dominik Jain 2024-01-08 18:01:04 +01:00
  • 789340f8d6
         Minor simplification in train_step (#1019) Michael Panchenko 2024-01-09 17:51:49 +01:00
  • f77d95da04 Fix: Missing type annotation of Experiment.watch_num_episodes Dominik Jain 2024-01-08 18:00:37 +01:00
  • 97a241a6fc Fix: DiscreteEnvironments.from_factory used incorrect EnvType Dominik Jain 2024-01-08 15:58:41 +01:00
  • 522f7fbf98
         Feature/dataclasses (#996) maxhuettenrauch 2023-12-30 11:09:03 +01:00
  • 5d09645a2c
         High-level API improvements (#1014) Michael Panchenko 2023-12-21 10:04:14 -06:00
  • da333d8a85 Fix incorrect use of platform-specific path separator Dominik Jain 2023-12-21 13:09:12 +01:00
  • e8cc80f990 Environments: Add option to a use a different factory for test envs to from_factory convenience construction mechanisms Dominik Jain 2023-12-18 12:52:05 +01:00
  • 45a1a3f259 SamplingConfig: Change default of repeat_per_collect to 1 (safest option) Dominik Jain 2023-12-14 18:53:25 +01:00
  • 408d51f9de SamplingConfig: Improve/extend docstrings, clearly explaining the parameters Dominik Jain 2023-12-14 18:52:20 +01:00
  • 294145aa3d
         Fix an example code in readme (#1011) Michael Yang 2023-12-15 01:46:56 -05:00
  • b7df31f2a7
         Docs/fix trainer fct notebooks (#1009) Carlo Cagnetta 2023-12-14 19:31:53 +01:00
  • 1903a72ecb Improve logging Dominik Jain 2023-12-14 11:53:05 +01:00
  • 3caa3805f0 Fix: SamplingConfig.start_timesteps_random was not used Dominik Jain 2023-12-14 11:47:32 +01:00
  • ea48cc2989
         Bump jupyter-server from 2.10.1 to 2.11.2 (#1003) dependabot[bot] 2023-12-06 12:24:43 +01:00
  • 34f89995f1
         Docs/overhaul (#999) Michael Panchenko 2023-12-06 09:55:46 +01:00
  • 4c24dc6441 Formatting Michael Panchenko 2023-12-05 23:46:54 +01:00
  • 5f4a02cc69 Docs: improve API landing page Michael Panchenko 2023-12-05 23:24:18 +01:00
  • 9d1440752e Deal with .jupyter_cache Michael Panchenko 2023-12-05 22:52:45 +01:00
  • c50e74f263 Fix rtd build, improvements in task running Michael Panchenko 2023-12-05 13:25:13 +01:00
  • 19e129d0cf Fix rtd build Michael Panchenko 2023-12-05 13:23:18 +01:00
  • 0b67447541 Docs: fixing spelling, re-adding spellcheck to pipeline Michael Panchenko 2023-12-05 13:22:04 +01:00
  • a846b52063 Typing: fixed multiple typing issues Michael Panchenko 2023-12-05 12:04:18 +01:00
  • 2e39a252e3 Docstring: minor changes to let ruff pass Michael Panchenko 2023-12-04 13:52:10 +01:00