Loading
0 Follower
0 Following
shadowyzy

Location

CN

Badges

0
0
0

Activity

May
Jun
Jul
Aug
Sep
Oct
Nov
Dec
Jan
Feb
Mar
Apr
May
Mon
Wed
Fri

Ratings Progression

Loading...

Challenge Categories

Loading...

Challenges Entered

Sample-efficient reinforcement learning in Minecraft

Latest submissions

See All
graded 25843
graded 25842
graded 25841
Participant Rating
Participant Rating
shadowyzy has not joined any teams yet...

NeurIPS 2019 : MineRL Competition

Why evaluation failed

Over 4 years ago

Evaluation failed.
The aicrowd-bot did not provide the Error log.

When will the results of round 1 be announced?

Over 4 years ago

Hi @BrandonHoughton, I have seen the notice. But I was confused that it tested my repo two weeks ago which is not my latest version.

The evaluation result does not match my local testing

Over 4 years ago

Thanks a lot! But the new maximum number of submissions is 25. That is too costly …

The evaluation result does not match my local testing

Over 4 years ago

I have a same problem.
Evaluation successful but only 1 episode with 4 steps.
But I used pytorch, and I don’t know what really happened.

Train a metacontroller based on Expert Data which is divided into several stages manually by reward

Over 4 years ago

Can I train a metacontroller based on Expert Data which is divided into several stages manually by reward, or does this count as hard coding?

Eg. stage 1 is the time when it has no reward .

How to explain this rule

Over 4 years ago

How to explain “A manually specified policy may not be used as a component of this model.” in the challenge rules ?
Can I define my own actions,such as define forward 3 frames continuously as “my foward” (just like skip frame), “craft stick from log” (at first frame craft planks, then craft stick) .

Can the agent get reward repeatedly?

Over 4 years ago

My agent run in “ObtainDiamond”, and it is rewarded repeatedly
It seems that the environment has some bug about it

Can the agent get reward repeatedly?

Over 4 years ago

Did he talk about this evaluation_locally.sh?
I can’t find anything about ObtainDiamond or ObtainDiamondDense.
By the way, in “MinerlObtainDiamond-v0” environment agent is rewarded repeatedly on my computer. Is it a bug? How to fix it …

This is evaluation_locally.sh.

#!/bin/bash
set -e


AICROWD_DATA_ENABLED="YES"
if [[ " $@ " =~ " --no-data " ]]; then
   AICROWD_DATA_ENABLED="NO"
else
    python3 ./utility/verify_or_download_data.py
fi


EXTRAOUTPUT=" > /dev/null 2>&1 "
if [[ " $@ " =~ " --verbose " ]]; then
   EXTRAOUTPUT=""
fi



# Run local name server
eval "pyro4-ns $EXTRAOUTPUT &"
trap "kill -11 $! > /dev/null 2>&1;" EXIT

# Run instance manager to generate performance report
export EVALUATION_STAGE='manager'
eval "python3 run.py --seeds 1 $EXTRAOUTPUT &"
trap "kill -11 $! > /dev/null 2>&1;" EXIT

# Run the evaluation
sleep 2
export MINERL_INSTANCE_MANAGER_REMOTE="1"
export EVALUATION_STAGE='testing'
export EVALUATION_RUNNING_ON='local'
export EXITED_SIGNAL_PATH='shared/exited'
rm -f $EXITED_SIGNAL_PATH
export ENABLE_AICROWD_JSON_OUTPUT='False'
eval "python3 run.py $EXTRAOUTPUT && touch $EXITED_SIGNAL_PATH || touch $EXITED_SIGNAL_PATH &"
trap "kill -11 $! > /dev/null 2>&1;" EXIT

# View the evaluation state
export ENABLE_AICROWD_JSON_OUTPUT='True'
python3 utility/parser.py || true
kill $(jobs -p)

Can the agent get reward repeatedly?

Over 4 years ago

In “MinerlObtainDiamond-v0” environment.

When agent get one stick, it has reward 4.
But if agent get two stick, can it has reward 8 ?
It seems that the current evalutation environment will give repeat reward.

shadowyzy has not provided any information yet.