Learning Multistage Robotic Manipulation Using Chained Options and Composable Subtask Rewards
Bibliographic record
Abstract
Applying reinforcement learning to robotic systems often requires a large number of interactions (or training samples) with the environment in order to discover effective behaviors. In this paper, we adapt the options framework, a popular form of hierarchical reinforcement learning, to improve sample efficiency in tasks that can be characterized by a sequence of subtasks. We present a new potential-based reward shaping and decomposition method that promotes subtask-level policy specialization and provides clearer interpretability of agent behavior while addressing the composite task. Building on this formulation, we develop an entropy-maximizing offpolicy method for options-based deep reinforcement learning that jointly learns distinct, interpretable policies across subtasks and automatically determines transition points within a unified end-to-end training scheme. To further enhance stability in subtask switching, we introduce a chained option execution strategy that integrates expert task knowledge. We evaluate the proposed approach in simulated high-dimensional robotic manipulation domains, including both 2D and 3D environments, on benchmark tasks such as pick-and-place and door opening.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| 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".