Isaac Kargar

Add new Scenario

2

Hi, I'm trying to use another scenario from scenario runner with carla_ad_demo. I put the scenario file `LaneChangeSimple.xosc` in the config folder next to the `FollowLeadingVehicle.xosc` file and change both...

send string data

2

Hello, Is it possible to send string data or key-value (like json) data from the board to helium network? I see in the library the `uint8_t appData[LORAWAN_APP_DATA_MAX_SIZE];` and I tried...

Hello, Is it possible to use this library with a custom board with esp32 chips? Thank you

[REQUEST] Adding model-based offline RL with image inputs like LOMPO and COMBO

8

**Is your feature request related to a problem? Please describe.** Model-based offline RL algorithms which are able to handle image inputs are necessary for some environments. **Describe the solution you'd...

Tensorflow on ARM

2

### Describe the Issue I want to run a trained tensorflow model on ARM cortex m3 32 bit. Is it possible? how can I do that? ### Steps to Reproduce...

Hi, Thank you for releasing the code. I have some questions about the 'done' situation in the cooperative navigation environment. I don't see any done function for the env. I...

Hi, Is there any subset of data? Or a version with a lower volume? it's more than 40 GB?

Run training faster

1

Hi, Is it possible to run the simulator faster for training the RL agent? It is too slow in real time

Dqn nonframe state

4

- Add dqn for non-frame state spaces - Add loading and evaluation code for the trained model

Multi-agent algorithm

4

I'm trying to use PPO_LSTM and R2D1 with a multi-agent environment. I was checking the other related [issue](https://github.com/astooke/rlpyt/issues/14) but it seems it was more about DDPG and not recurrent models....