hongshaorou/Tianshou
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
653 Commits 3 Branches 28 Tags
Commit Graph

15 Commits

Author SHA1 Message Date
Daniel Plop
8a0629ded6
Fix mypy issues in tests and examples (#1077) 
Closes #952 

- `SamplingConfig` supports `batch_size=None`. #1077
- tests and examples are covered by `mypy`. #1077
- `NetBase` is more used, stricter typing by making it generic. #1077
- `utils.net.common.Recurrent` now receives and returns a
`RecurrentStateBatch` instead of a dict. #1077

---------

Co-authored-by: Michael Panchenko <m.panchenko@appliedai.de>
 2024-04-03 18:07:51 +02:00
Dominik Jain
1714c7f2c7
High-level API: Fix number of test episodes being incorrectly scaled by number of envs (#1071) 2024-03-07 08:57:11 -08:00
Dominik Jain
bf391853dc Allow to configure number of test episodes in high-level API 2024-02-14 19:14:28 +01:00
Dominik Jain
45a1a3f259 SamplingConfig: Change default of repeat_per_collect to 1 (safest option) 2023-12-21 13:13:51 +01:00
Dominik Jain
408d51f9de SamplingConfig: Improve/extend docstrings, clearly explaining the parameters 2023-12-21 13:13:51 +01:00
Dominik Jain
dae4000cd2 Revert "Depend on sensAI instead of copying its utils (logging, string)" 
This reverts commit fdb0eba93d81fa5e698770b4f7088c87fc1238da.
 2023-11-08 19:11:39 +01:00
Dominik Jain
fdb0eba93d Depend on sensAI instead of copying its utils (logging, string) 2023-10-27 20:15:58 +02:00
Dominik Jain
d684dae6cd Change default number of environments (train=#CPUs, test=1) 2023-10-26 12:50:08 +02:00
Dominik Jain
e63d8d4147 Use ToStringMixin in dataclasses to detect recurring objects in larger object trees 2023-10-18 20:44:18 +02:00
Dominik Jain
d269063e6a Remove 'RL' prefix from class names 2023-10-18 20:44:17 +02:00
Dominik Jain
1cba589bd4 Add DQN support in high-level API 
* Allow to specify trainer callbacks (train_fn, test_fn, stop_fn)
  in high-level API, adding the necessary abstractions and pass-on
  mechanisms
* Add example atari_dqn_hl
 2023-10-18 20:44:16 +02:00
Dominik Jain
2671580c6c Add DDPG high-level API and MuJoCo example 2023-10-18 20:44:16 +02:00
Dominik Jain
6b6d9ea609 Add support for discrete PPO 
* Refactored module `module` (split into submodules)
* Basic support for discrete environments
* Implement Atari env. factory
* Implement DQN-based actor factory
* Implement notion of reusing agent preprocessing network for critic
* Add example atari_ppo_hl
 2023-10-18 20:44:16 +02:00
Dominik Jain
e993425aa1 Add high-level API support for TD3 
* Created mixins for agent factories to reduce code duplication
 * Further factorised params & mixins for experiment factories
 * Additional parameter abstractions
 * Implement high-level MuJoCo TD3 example
 2023-10-18 20:44:16 +02:00
Dominik Jain
8ec42009cb Move RLSamplingConfig to separate module config, fixing cyclic import 2023-10-09 13:02:23 +02:00