Skip to content

Hindsight Experience Replay Buffer#84

Open
prabhatnagarajan wants to merge 48 commits into
pfnet:masterfrom
prabhatnagarajan:her
Open

Hindsight Experience Replay Buffer#84
prabhatnagarajan wants to merge 48 commits into
pfnet:masterfrom
prabhatnagarajan:her

Conversation

@prabhatnagarajan

@prabhatnagarajan prabhatnagarajan commented Oct 28, 2020

Copy link
Copy Markdown
Contributor

Depends on #80.
Resolves #6.

Results:

her_bit_flip_dqn

@prabhatnagarajan

Copy link
Copy Markdown
Contributor Author

/test

@pfn-ci-bot

Copy link
Copy Markdown

Successfully created a job for commit 71809a5:

@prabhatnagarajan

Copy link
Copy Markdown
Contributor Author

/test

@pfn-ci-bot

Copy link
Copy Markdown

Successfully created a job for commit 9721d1a:

@prabhatnagarajan

Copy link
Copy Markdown
Contributor Author

/test

@pfn-ci-bot

Copy link
Copy Markdown

Successfully created a job for commit 8643e0d:

Comment thread examples/her/train_dqn_bit_flip.py Outdated
prabhatnagarajan and others added 2 commits October 30, 2020 04:15
Co-authored-by: Justin DuJardin <justindujardin@users.noreply.github.com>
@pfn-ci-bot

Copy link
Copy Markdown

Successfully created a job for commit 573c7a2:

@prabhatnagarajan

Copy link
Copy Markdown
Contributor Author

/test

@pfn-ci-bot

Copy link
Copy Markdown

Successfully created a job for commit ed4ae2e:

@prabhatnagarajan

Copy link
Copy Markdown
Contributor Author

Current results
PickAndPlace
Push
Slide

@prabhatnagarajan

Copy link
Copy Markdown
Contributor Author

/test

@pfn-ci-bot

Copy link
Copy Markdown

Successfully created a job for commit ef230a4:

@ummavi

ummavi commented May 20, 2021

Copy link
Copy Markdown
Member

/test

@pfn-ci-bot

Copy link
Copy Markdown

Successfully created a job for commit 35f085c:

success = (
self.observation["desired_goal"] == self.observation["achieved_goal"]
).all()
return (self.steps >= self.n) or success, success

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think I should use the wrapper ContinuingTimeLimit actually. Exceeding the number of timesteps should not be a terminal signal.

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.

Hindsight Experience Replay

5 participants