BaRC: Backward Reachability Curriculum for Robotic Reinforcement\n Learning
Bibliographic record
Abstract
Model-free Reinforcement Learning (RL) offers an attractive approach to learn\ncontrol policies for high-dimensional systems, but its relatively poor sample\ncomplexity often forces training in simulated environments. Even in simulation,\ngoal-directed tasks whose natural reward function is sparse remain intractable\nfor state-of-the-art model-free algorithms for continuous control. The\nbottleneck in these tasks is the prohibitive amount of exploration required to\nobtain a learning signal from the initial state of the system. In this work, we\nleverage physical priors in the form of an approximate system dynamics model to\ndesign a curriculum scheme for a model-free policy optimization algorithm. Our\nBackward Reachability Curriculum (BaRC) begins policy training from states that\nrequire a small number of actions to accomplish the task, and expands the\ninitial state distribution backwards in a dynamically-consistent manner once\nthe policy optimization algorithm demonstrates sufficient performance. BaRC is\ngeneral, in that it can accelerate training of any model-free RL algorithm on a\nbroad class of goal-directed continuous control MDPs. Its curriculum strategy\nis physically intuitive, easy-to-tune, and allows incorporating physical priors\nto accelerate training without hindering the performance, flexibility, and\napplicability of the model-free RL algorithm. We evaluate our approach on two\nrepresentative dynamic robotic learning problems and find substantial\nperformance improvement relative to previous curriculum generation techniques\nand naive exploration strategies.\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 distilled prediction
Teacher imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.003 | 0.004 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".