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

11 Commits

Author SHA1 Message Date
Dominik Jain
41bd463a7b Allow to configure activation function in default networks 
* Set ReLU as default in all actor and critic factories
* Configure non-default in applicable MuJoCo examples
 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
799beb79b4 Support discrete SAC in high-level API 
* Changed machanism for reusing actor's preprocessing module in critics
  to avoid special handling in AgentFactory implementations, improving
  separation of concerns:
    - Added CriticFactoryReuseActor as the new critic factory
    - Added ActorFactoryTransientStorageDecorator to pass on the actor
      data
    - Added helper classes ActorFuture, ActorFutureProviderProtocol
* Add example atari_sac_hl
 2023-10-18 20:44:17 +02:00
Dominik Jain
17ef4dd5eb Support REDQ in high-level API 
* Implement example mujoco_redq_hl
* Add abstraction CriticEnsembleFactory with default implementations
  to suit REDQ
* Fix type annotation of linear_layer in Net, MLP, Critic
  (was incompatible with REDQ usage)
 2023-10-18 20:44:17 +02:00
Dominik Jain
1bb52a6a5c Simplify critic/agent with optimizer generation 
After adding a function to create ModuleOpt instances directly from
AgentFactory and CriticFactory,
  * several mixins for AgentFactories are no longer needed (deleted)
  * additional abstractions for ModuleOptFactories are no longer needed (deleted)
 2023-10-18 20:44:17 +02:00
Dominik Jain
6bb3abb2f0 Support PG/Reinforce in high-level API 
* Add example mujoco_reinforce_hl
* Extended functionality of ActorFactory to support creation of ModuleOpt
 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
b54fcd12cb Change high-level DQN interface to expect an actor instead of a critic, 
because that is what is functionally required
 2023-10-18 20:44:16 +02:00
Dominik Jain
9f0a410bb1 Log full experiment configuration, adding string representations to relevant classes 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