Fixed reinforcement learning to run with any screen size; added diagram #389
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
soumith
reviewed
Dec 18, 2018
| @@ -23,7 +23,10 @@ | |||
| As the agent observes the current state of the environment and chooses | |||
| an action, the environment *transitions* to a new state, and also | |||
| returns a reward that indicates the consequences of the action. In this | |||
| task, the environment terminates if the pole falls over too far. | |||
| task, rewards are +1 for every incremental timestep and the environment | |||
| terminates if the pole falls over too far or the crat mover more then 2.4 | |||
soumith
reviewed
Dec 18, 2018
| policy_net = DQN().to(device) | ||
| target_net = DQN().to(device) | ||
| # Get screen size so that we can initialize layers correctly based on shape | ||
| # returned from AI gym. Typical dimentions at this pont are close to 3x40x90 |
soumith
reviewed
Dec 18, 2018
| # which is the result of a clamped and down-scaled buffer in get_screen() | ||
| init_screen = get_screen() | ||
| _, _, screen_height, screen_width = init_screen.shape | ||
| #screen_height = init_screen.shape[2] |
|
the two failures are because of the mnist deadlock appearing again cc: @yf225 |
rodrigo-techera
pushed a commit
to Experience-Monks/tutorials
that referenced
this pull request
Nov 29, 2021
Fixed reinforcement learning to run with any screen size; added diagram
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Outdated suggestions cannot be applied.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.
Fixed reinforcement learning to run with different screen sizes (it looks like the resolution coming in was incorrect, which caused the wrong screen subregion to be accessed and training fo fail).
Also, added some improved comments in the tutorial and a diagram of data-plow to make things more understandable.
Don't merge until it passes tests (we see tutorial updated).