MétaCan
Menu
Back to cohort
Record W4293863172 · doi:10.1109/siu55565.2022.9864806

Autonomous Driving Systems for Decision-Making Under Uncertainty Using Deep Reinforcement Learning

2022· article· en· W4293863172 on OpenAlex
Mehmet Haklıdır, Hakan Temeltaş

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

Venue2022 30th Signal Processing and Communications Applications Conference (SIU) · 2022
Typearticle
Languageen
FieldComputer Science
TopicReinforcement Learning in Robotics
Canadian institutionsStantec (Canada)
Fundersnot available
KeywordsPartially observable Markov decision processReinforcement learningMarkov decision processComputer scienceArtificial intelligenceAction (physics)Process (computing)ObservableControl (management)Markov processState (computer science)Autonomous agentMarkov chainMachine learningMarkov modelMathematics

Abstract

fetched live from OpenAlex

Deep reinforcement learning has achieved human-level and even beyond performance on complex tasks like Atari games and Go. However, this performance is not easy to adapt to autonomous driving since real world state spaces are extremely complex and have continuous action spaces. Besides, autonomous driving tasks often require decision making under uncertainty. Hence, the autonomous driving problem can be formulated as a partially observable Markov decision process (POMDP).In this paper, we propose a new approach to solve the autonomous driving problem based on decision making under uncertainty as a partially observable Markov decision process, using Guided Soft Actor-Critic (Guided SAC). Self driving car has been trained for the scenario where it encountered with a pedestrian crossing the road. Experiments show that the control agent exhibits desirable control behavior and performed close to the fully observable state under various uncertainty situations.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Science and technology studies
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.920
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0060.000
Scholarly communication0.0010.001
Open science0.0030.002
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.040
GPT teacher head0.308
Teacher spread0.268 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it