-
our few next steps...
-
In order to avoid code duplication, it might be useful if you could package all of you existing _featurizers_ within a single library.
For the moment, I copied all of the following files within the …
-
Hi,
Thanks for your nice work. I want to train an RNN agent with sequential data and I tested it with dm_control_suite. The paper mentioned that: "For sequence data, we also provide future states,…
-
-
Having read the [docs](https://github.com/deepmind/acme/blob/master/docs/components.md) and the code for the [episode adder](https://github.com/deepmind/acme/blob/master/acme/adders/reverb/episode.py#…
-
If I increase both the HEIGHT and WIDTH from 5 to 10 keeping the obstacles and the final goal at the same position, Deep SARSA network doesn't seem to converge. What do you think is the problem? Shoul…
-
Example 6.6 of Sutton's book,
![image](https://user-images.githubusercontent.com/13688320/86022630-36108a80-ba5d-11ea-847e-e67d75b38f1d.png)
![image](https://user-images.githubusercontent.com/136883…
-
Hello,
I am running your sarsa_resco.py code with a custom environment, representing downtown Athens so around 30-40 traffic lights. When I added the custom environment to the simulation, I get the…
-
Russel & Norvig p. 842, Fig 21.8 (p.844), all refs to 3rd edition, use a generalized exploration function, which allows for the agent to decrease or stop exploration over time. They define a function…
-
```
Create a page for the Mines environment, give a little background, and then
link to it from everywhere to give it some context.
```
Original issue reported on code.google.com by `brian.ta...@gmai…