Skip to content
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

fine tune PER, fix bugs #131

Merged
merged 33 commits into from
Apr 27, 2017
Merged

fine tune PER, fix bugs #131

merged 33 commits into from
Apr 27, 2017

Conversation

kengz
Copy link
Owner

@kengz kengz commented Apr 26, 2017

Bug Fixes, Improvements

  • fix overflow error in np.exp of SoftmaxPolicy, BoltzmannPolicy by casting to float64 instead of float32
  • improve overall np.isfinite asserts
  • remove index after reset in *analysis.csv
  • remove unused specs
  • reorganize and expand test specs
  • guard continuous action value range in continuous policies
  • fix analytics param variable sourcing

DDPG

  • add EpsilonGreedyNoisePolicy

PER

  • add memory.update(errors) throughout all agents
  • add shape assert for Q values and errors throughout
  • auto max_mem_len as max_timestep * max_epis/3 if not specified
  • put the missing abs for init reward

@kengz kengz merged commit 4f123b8 into master Apr 27, 2017
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant