Locally Persistent Exploration in Continuous Control Tasks with Sparse\n Rewards
Bibliographic record
Abstract
A major challenge in reinforcement learning is the design of exploration\nstrategies, especially for environments with sparse reward structures and\ncontinuous state and action spaces. Intuitively, if the reinforcement signal is\nvery scarce, the agent should rely on some form of short-term memory in order\nto cover its environment efficiently. We propose a new exploration method,\nbased on two intuitions: (1) the choice of the next exploratory action should\ndepend not only on the (Markovian) state of the environment, but also on the\nagent's trajectory so far, and (2) the agent should utilize a measure of spread\nin the state space to avoid getting stuck in a small region. Our method\nleverages concepts often used in statistical physics to provide explanations\nfor the behavior of simplified (polymer) chains in order to generate persistent\n(locally self-avoiding) trajectories in state space. We discuss the theoretical\nproperties of locally self-avoiding walks and their ability to provide a kind\nof short-term memory through a decaying temporal correlation within the\ntrajectory. We provide empirical evaluations of our approach in a simulated 2D\nnavigation task, as well as higher-dimensional MuJoCo continuous control\nlocomotion tasks with sparse rewards.\n
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".