Improving Reinforcement Learning with Human Assistance: An Argument for\n Human Subject Studies with HIPPO Gym
Bibliographic record
Abstract
Reinforcement learning (RL) is a popular machine learning paradigm for game\nplaying, robotics control, and other sequential decision tasks. However, RL\nagents often have long learning times with high data requirements because they\nbegin by acting randomly. In order to better learn in complex tasks, this\narticle argues that an external teacher can often significantly help the RL\nagent learn.\n OpenAI Gym is a common framework for RL research, including a large number of\nstandard environments and agents, making RL research significantly more\naccessible. This article introduces our new open-source RL framework, the Human\nInput Parsing Platform for Openai Gym (HIPPO Gym), and the design decisions\nthat went into its creation. The goal of this platform is to facilitate\nhuman-RL research, again lowering the bar so that more researchers can quickly\ninvestigate different ways that human teachers could assist RL agents,\nincluding learning from demonstrations, learning from feedback, or curriculum\nlearning.\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 | 0.008 | 0.027 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.007 |
| Scholarly communication | 0.002 | 0.006 |
| Open science | 0.002 | 0.004 |
| Research integrity | 0.002 | 0.004 |
| Insufficient payload (model declined to judge) | 0.012 | 0.002 |
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".