This repository was archived by the owner on May 6, 2021. It is now read-only.
fix IQN #53
Merged
fix IQN #53
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
findmyway
approved these changes
Jun 24, 2020
Comment on lines
+187
to
+190
| aₜ = argmax(mean(zₜ, dims = 2), dims = 1) | ||
| aₜ = aₜ .+ typeof(aₜ)(CartesianIndices((0, 0:N′-1, 0))) | ||
| qₜ = reshape(zₜ[aₜ], :, batch_size) | ||
| target = reshape(r, 1, batch_size) .+ learner.γ * reshape(1 .- t, 1, batch_size) .* qₜ # reshape to allow broadcast |
Member
Not so bad. By the way, I fixed a subtle but important bug at JuliaReinforcementLearning/ReinforcementLearningCore.jl#83 According to my test, the result with Rainbow should be aligned with those in Dopamine. https://google.github.io/dopamine/baselines/plots.html |
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
Experiments on pong seem stable now (trained for 6M steps). The expected duration of the whole experiment is 8 days on a Tesla V100-SXM2. Is this fast or slow? (I guess I should compare at some point to rays RLlib).