Clarification on input sensors during evaluation

The evaluator code in the starter kit does not allow Segmentation cameras during 1-hr practice session. Is the evaluator on the server different from the starter-kit ?

link to code line

View post 0

Safety Infractions calculation during Stage 2 1-Hour practice period

@siddha_ganju @jon_francis can you please clarify my doubt?

View post 0

Safety Infractions calculation during Stage 2 1-Hour practice period

Does the evaluation metric (as shown on the Stage 2 leaderboard) include safety infractions happened during the 1-hour training session, or does it include only those infractions happened during the final 3 episodes evaluation?

View post 0

Regarding Stage 2 evaluation

@Arav-Agarwal @siddha_ganju

View post 0

Regarding Stage 2 evaluation

The documentation states that during stage 2, the teams will upload their models “with initialization”, this model will have 1 hour of training time to learn the new track and then it will be evaluated on that track.
Does this mean that we can upload pretrained networks/models during the stage 2 as well. In not then what exactly does initialization means here?

View post 1

Get input actions given directly to simulator for creating Imitation Learning data

Create a simple pygame program which takes input from keyboard, and displays frames.
Pass the input to the simulator and display the RGB images on pygame window. According to your requirement either save the image,input pair in memory and dump them altogether at the end of the episode or save as it is collected.

View post 1

Clarification on input sensors during evaluation

The wording is a bit unclear to me, During the “evaluation” there is “practice” session of 1 Hour and then the final “evaluation”. My question is regarding the “practice” session, are we allowed to use any sensor during the practice session or only the three (Front Left and Right) ?

View post 1

Clarification on input sensors during evaluation

For Round 2, can we use additional sensors for 1-hour training period ? Like segmentation camera view for the new track ?

View post 0

Get input actions given directly to simulator for creating Imitation Learning data

@max333 Agreed on not using record_manually, I came to understand this when I solved my original problem as mentioned below:
Although I did not used BaseAgent class, I wrote a small pygame wrapper over the env, to take input from keyboard and display the screen inside pygame (I can still see the car in simulator, since the pygame window is small) and recorded my observations that way.
Thanks for your inputs.

View post 2

Get input actions given directly to simulator for creating Imitation Learning data

I am trying to record a human-performed demo using the env.record_manually function. I am able to get observations but not the actions. I assume this is because during record_manually the actions are fed via Keyboard to the simulator and not through env.step and thus not captured anywhere in the python code. Can we query the simulator to get last action performed ? Or can we recover action somehow ?

If not record_manually, is there an another way to get actions+observations while driving the car ourselves?

View post 2