Learning to Predict Consequences as a Method of Knowledge Transfer in Reinforcement Learning
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.
Bibliographic record
Abstract
The reinforcement learning (RL) paradigm allows agents to solve tasks through trial-and-error learning. To be capable of efficient, long-term learning, RL agents should be able to apply knowledge gained in the past to new tasks they may encounter in the future. The ability to predict actions' consequences may facilitate such knowledge transfer. We consider here domains where an RL agent has access to two kinds of information: agent-centric information with constant semantics across tasks, and environment-centric information, which is necessary to solve the task, but with semantics that differ between tasks. For example, in robot navigation, environment-centric information may include the robot's geographic location, while agent-centric information may include sensor readings of various nearby obstacles. We propose that these situations provide an opportunity for a very natural style of knowledge transfer, in which the agent learns to predict actions' environmental consequences using agent-centric information. These predictions contain important information about the affordances and dangers present in a novel environment, and can effectively transfer knowledge from agent-centric to environment-centric learning systems. Using several example problems including spatial navigation and network routing, we show that our knowledge transfer approach can allow faster and lower cost learning than existing alternatives.
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 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 | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.002 |
| 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 it