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

25 Commits

Author SHA1 Message Date
Dominik Jain
20074931d5 Improve docstrings 2024-01-16 14:52:31 +01:00
Dominik Jain
05a8cf4e74 Refactoring, improving class name EnvFactoryGymnasium -> EnvFactoryRegistered 2024-01-16 14:52:31 +01:00
Dominik Jain
c9cb41bf55 Make envpool usage configuration more explicit 2024-01-16 14:52:31 +01:00
Dominik Jain
eaab7b0a4b Improve environment factory abstractions in high-level API: 
* EnvFactory now uses the creation of a single environment as
   the basic functionality which the more high-level functions build
   upon
 * Introduce enum EnvMode to indicate the purpose for which an env
   is created, allowing the factory creation process to change its
   behaviour accordingly
 * Add EnvFactoryGymnasium to provide direct support for envs that
   can be created via gymnasium.make
     - EnvPool is supported via an injectible EnvPoolFactory
     - Existing EnvFactory implementations are now derived from
       EnvFactoryGymnasium
 * Use a separate environment (which uses new EnvMode.WATCH) for
   watching agent performance after training (instead of using test
   environments, which the user may want to configure differently)
 2024-01-12 17:13:42 +01:00
Dominik Jain
97a241a6fc Fix: DiscreteEnvironments.from_factory used incorrect EnvType 2024-01-08 15:58:41 +01:00
Dominik Jain
e8cc80f990 Environments: Add option to a use a different factory for test envs 
to `from_factory` convenience construction mechanisms
 2023-12-21 13:13:51 +01:00
Michael Panchenko
2e39a252e3 Docstring: minor changes to let ruff pass 2023-12-04 13:52:46 +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
96298eafd8 Add convenient construction mechanisms for Environments 
(based on factory function for a single environment)
 2023-10-25 21:20:07 +02:00
Dominik Jain
b5a891557f Revert to simplified environment factory, removing unnecessary config object 
(configuration shall be part of the factory instance)
 2023-10-24 13:14:23 +02:00
Dominik Jain
6cbee188b8 Change interface of EnvFactory to ensure that configuration 
of number of environments in SamplingConfig is used
(values are now passed to factory method)

This is clearer and removes the need to pass otherwise
unnecessary configuration to environment factories at
construction
 2023-10-19 11:37:20 +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
4b270eaa2d Add documentation, improve structure of 'module' package 2023-10-18 20:44:18 +02:00
Dominik Jain
023b33c917 Make mypy happy 2023-10-18 20:44:18 +02:00
Dominik Jain
3691ed2abc Support obs_rms persistence for MuJoCo by adding a general mechanism 
for attaching persistence to Environments instances
 2023-10-18 20:44:17 +02:00
Dominik Jain
73a6d15eee Log Environments 2023-10-18 20:44:17 +02:00
Dominik Jain
a161a9cf58 Improve type annotations, fix type issues and add checks 2023-10-18 20:44:17 +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
Michael Panchenko
5bcf514c55 Add alternative functional interface for environment creation 
where a persistable configuration object is passed as an
argument, as this can help to ensure persistability (making the
requirement explicit)
 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
367778d37f Improve high-level policy parametrisation 
Policy objects are now parametrised by converting the parameter
dataclass instances to kwargs, using some injectable conversions
along the way
 2023-10-18 20:44:16 +02:00
Dominik Jain
37dc07e487 Add high-level experiment builder interface 2023-10-18 20:44:05 +02:00
Dominik Jain
316eb3c579 Add SAC high-level interface 2023-10-09 13:02:01 +02:00
Dominik Jain
16ed5fd2a5 Initial high-level interfaces, demonstrated in mujoco_ppo_hl 2023-10-09 13:01:35 +02:00