New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
A2C cartpole benchmark #180
Merged
Merged
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
6 tasks
This was referenced Sep 24, 2018
6 tasks
This was referenced Oct 1, 2018
6 tasks
This was referenced Oct 2, 2018
This was referenced Oct 3, 2018
Merged
This was referenced Oct 5, 2018
Merged
This was referenced Oct 25, 2018
Merged
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Outdated suggestions cannot be applied.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.
Experiment Result
Abstract
Benchmark experiment for A2C on the Cartpole environment
Methods
To Reproduce
Results
All the results contributed will be added to the benchmark, and made publicly available on Dropbox.
Discussion (optional)
Looking at the experiment graph, we can tell some effects from the hyperparameters. Going from left to right columns:
entropy_coef
(this encourages exploration with larger value): the larger the entropy coef, the slower the convergence. For such a simple environment as cartpole, agent does not need much exploration, so low coef leads to faster learning. Some entropy is still beneficial. Convergence speed peaks atentropy_coef=0.02
lambda
(of GAE): performance is not sensitive to it, but high value can cause some drop in strength.training_frequency
(per episode for OnPolicyReplay): as seen, training cannot happen too frequently (high variance) or infrequently (slow learning). There is an optimal frequency for maximum convergence speed, which is 2 for this experiment.hid_layers_activation
: tanh works the best overall.lr_decay_frequency
(lr = learning rate): the strength is concentrated at high value for frequency at 2k; the speed graph has a peak at 2k (one outlier point); the stability graph has a noticeable bump peaking at 4k to 6k. Overall it seems that if decay frequency is too high, learning rate drops very low very quickly, and learning slows down. If lr drops too slow, lr stays high, so learning is unstable. There is an optimal point in between. The effect can be quite noisy.