Proximal Policy Optimization example #470
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
…fluence on results)
wrzadkow
force-pushed
the
rl-example-ppo
branch
from
b809cea to
1af5bbb
Compare
jheek
requested changes
Sep 18, 2020
andsteing
reviewed
Sep 18, 2020
lespeholt
reviewed
Sep 24, 2020
wrzadkow
force-pushed
the
rl-example-ppo
branch
4 times, most recently
from
d411337 to
1e89a8b
Compare
wrzadkow
force-pushed
the
rl-example-ppo
branch
from
1e89a8b to
7e036ae
Compare
wrzadkow
force-pushed
the
rl-example-ppo
branch
from
5e3eb19 to
08bd344
Compare
wrzadkow
force-pushed
the
rl-example-ppo
branch
from
aeabf2a to
a4dade8
Compare
jheek
reviewed
Oct 1, 2020
copybara-service bot
pushed a commit
that referenced
this pull request
Oct 1, 2020
PiperOrigin-RevId: 334765232
Merged
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
6 participants
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Outdated suggestions cannot be applied.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.
Reinforcement learning example using the Proximal Policy Optimization algorithm, prepared in close collaboration with @jheek and @lespeholt .
The implementation learns to play Atari games implemented in OpenAI gym environment. Tests on BeamRider, Breakout, Pong, Qbert, Seaquest, and SpaceInvaeders show that the training performance from the original paper is reproduced. The speed is ~1000 FPS on a VM with one V100 GPU. Unit tests and documentation are provided.