Integrating hydra with DQN #201
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
facebook-github-bot
added
the
CLA Signed
vmoens
reviewed
Jun 16, 2022
examples/ddpg/ddpg.py
Outdated
|
|
||
| actor_model_explore = model[0] | ||
| if args.ou_exploration: | ||
| if args.gSDE: | ||
| if cfg.ou_exploration: |
There was a problem hiding this comment.
can we delete ou_exploration and gSDE from DQN? they make no sense here. Ideally they shouldn't even be in the config
…v_dqn # Conflicts: # examples/ddpg/ddpg.py # examples/dqn/dqn.py # examples/redq/redq.py # examples/sac/sac.py
vmoens
reviewed
Jun 16, 2022
| @@ -10,7 +10,6 @@ | |||
| import hydra | |||
There was a problem hiding this comment.
I'm not sure where do those changes in PPO come from in this PR
vmoens
reviewed
Jun 16, 2022
torchrl/trainers/helpers/models.py
Outdated
| @@ -1351,3 +1351,5 @@ class DiscreteModelConfig: | |||
| # whether a distributional loss should be used. | |||
| atoms: int = 51 | |||
| # number of atoms used for the distributional loss | |||
| gSDE: bool = False | |||
There was a problem hiding this comment.
Yeah let's not do that :) No gSDE for discrete actions
There was a problem hiding this comment.
I removed epsilon greedy wrapper which removed the error with action_value being None, is this ok?
vmoens
reviewed
Jun 16, 2022
vmoens
reviewed
Jun 21, 2022
examples/dqn/dqn.py
Outdated
| @@ -103,17 +101,8 @@ def main(cfg: "DictConfig"): | |||
| ) | |||
|
|
|||
| loss_module, target_net_updater = make_dqn_loss(model, cfg) | |||
| model_explore = EGreedyWrapper(model, annealing_num_steps=cfg.annealing_frames).to( | |||
There was a problem hiding this comment.
I think we still want that, that's the typical exploration technique for dqn
| @@ -124,7 +113,7 @@ def main(cfg: "DictConfig"): | |||
|
|
|||
| collector = make_collector_offpolicy( | |||
| make_env=create_env_fn, | |||
| actor_model_explore=model_explore, | |||
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Integrated hydra with DQN using structured configs.