Improved sample efficiency by episodic memory hit ratio deep Q-networks
Bibliographic record
Abstract
Deep Reinforcement Learning (DRL) has achieved great success in making decisions on some complex tasks. Unfortunately, existing DRL algorithms are usually sample inefficient in that they require a huge amount of interactions with the environment to gain a desirable performance. Recently, Episodic Memory Deep Q-Networks (EMDQN) substantially improves the sample efficiency by episodic memory. However, rewards in episodic memory are delayed because they are obtained after the agent interacts with the environment in a multi-step trial and error manner, which means that EMDQN is sample inefficient to some extent. In this paper, we propose a new algorithm, Episodic Memory Hit Ratio DQN (EMHR-DQN), to improve sample efficiency by reward shaping. Inspired by reward shaping methods, we design a new reward shaping function Episodic Memory Hit Ration (EMHR) to provide additional rewards for the retrieval result of episodic memory. In this way, our method can modify rewards in episodic memory and provide useful supervision for the training of the agent. Experimental results verify the superiority of our method.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".