[RLlib] Trajectory view API: enable by default for SAC, DDPG, DQN, SimpleQ #11827
Conversation
This file contains 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
…ectory_view_api_plumbing_only
…ectory_view_api_plumbing_only
…ectory_view_api_plumbing_only � Conflicts: � rllib/policy/eager_tf_policy.py
…ectory_view_api_enable_by_default_for_some_tf
…ectory_view_api_enable_by_default_for_some_tf
…ectory_view_api_enable_by_default_for_some_tf � Conflicts: � rllib/policy/dynamic_tf_policy.py � rllib/policy/eager_tf_policy.py � rllib/policy/policy.py � rllib/policy/tf_policy_template.py � rllib/utils/tf_ops.py
…ectory_view_api_enable_by_default_for_some_tf
… trajectory_view_api_enable_by_default_for_sac_dqn_ddpg
sven1977
changed the title
…ectory_view_api_enable_by_default_for_sac_dqn_ddpg � Conflicts: � rllib/agents/maml/maml_torch_policy.py � rllib/execution/train_ops.py
ericl
approved these changes
Nov 12, 2020
…ectory_view_api_enable_by_default_for_sac_dqn_ddpg
|
Seems there is some DQN learning regression. |
ericl
added
the
@author-action-required
…ectory_view_api_enable_by_default_for_sac_dqn_ddpg
sven1977
deleted the
trajectory_view_api_enable_by_default_for_sac_dqn_ddpg
branch
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Outdated suggestions cannot be applied.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.
This PR is based on #11747 (which needs to be merged first!)
It enables the trajectory view API by default for: DDPG, DQN, SimpleQ, and SAC (on tf, tfe, tf2, and torch).
Why are these changes needed?
Related issue number
Checks
scripts/format.shto lint the changes in this PR.