MétaCan
Menu
Back to cohort
Record W4404201236 · doi:10.1016/j.neucom.2024.128836

Improved exploration–exploitation trade-off through adaptive prioritized experience replay

2024· article· en· W4404201236 on OpenAlex

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

VenueNeurocomputing · 2024
Typearticle
Languageen
FieldComputer Science
TopicDistributed and Parallel Computing Systems
Canadian institutionsWestern University
Fundersnot available
KeywordsComputer science

Abstract

fetched live from OpenAlex

Experience replay is an indispensable part of deep reinforcement learning algorithms that enables the agent to revisit and reuse its past and recent experiences to update the network parameters. In many baseline off-policy algorithms, such as deep Q-networks (DQN), transitions in the replay buffer are typically sampled uniformly. This uniform sampling is not optimal for accelerating the agent’s training towards learning the optimal policy. A more selective and prioritized approach to experience sampling can yield improved learning efficiency and performance. In this regard, this work is devoted to the design of a novel prioritizing strategy to adaptively adjust the sampling probabilities of stored transitions in the replay buffer. Unlike existing sampling methods, the proposed algorithm takes into consideration the exploration-exploitation trade-off (EET) to rank transitions, which is of utmost importance in learning an optimal policy. Specifically, this approach utilizes temporal difference and Bellman errors as criteria for sampling priorities. To maintain balance in EET throughout training, the weights associated with both criteria are dynamically adjusted when constructing the sampling priorities. Additionally, any bias introduced by this sample prioritization is mitigated through assigning importance-sampling weight to each transition in the buffer. The efficacy of this prioritization scheme is assessed through training the DQN algorithm across various OpenAI Gym environments. The results obtained underscore the significance and superiority of our proposed algorithm over state-of-the-art methods. This is evidenced by its accelerated learning pace, greater cumulative reward, and higher success rate. • A novel sample prioritization is proposed for deep Q-Networks. • Temporal difference and Bellman errors are employed to construct the priority score. • Weights of augmented errors into the priority score are adaptively updated. • The weighted priority balances the exploration-exploitation trade-off. • This score yields significant improvement over baselines across Gym environments.

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)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.937
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0010.002
Open science0.0010.000
Research integrity0.0000.000
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 head0.288
Teacher spread0.248 · 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