paper-with-me

홈 › Papers

Regulating Reward Training by Means of Certainty Prediction in a Neural Network-Implemented Pong Game

2016-09-23 · Matt Oberdorfer, Matt Abuzalaf

We present the first reinforcement-learning model to self-improve its reward-modulated training implemented through a continuously improving "intuition" neural network. An agent was trained how to play the arcade video game Pong with two reward-based alternatives, one where the paddle was placed randomly during training, and a second where the paddle was simultaneously trained on three additional neural networks such that it could develop a sense of "certainty" as to how probable its own predicted paddle position will be to return the ball. If the agent was less than 95% certain to return the ball, the policy used an intuition neural network to place the paddle. We trained both architectures for an equivalent number of epochs and tested learning performance by letting the trained programs play against a near-perfect opponent. Through this, we found that the reinforcement learning model that uses an intuition neural network for placing the paddle during reward training quickly overtakes the simple architecture in its ability to outplay the near-perfect opponent, additionally outscoring that opponent by an increasingly wide margin after additional epochs of training.

📄 PDF Abstract BibTeX arXiv:1609.07434

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Why Semantic Entropy Fails: Geometry-Aware and Calibrated Uncertainty for Policy Optimization

2026-05-20 · Zheyuan Zhang, Kaiwen Shi, Han Bao, Zehong Wang 외 arxiv

Post-training has become central to improving reasoning and alignment in large language models, where critic-free models enable scalable learning from model-generated outputs but lack principled mechanisms to distinguish…

Robust Model Predictive Techno-Economic Control of Active Distribution Networks

2023-05-05 · Salish Maharjan, Prashant Tiwari, Rui Cheng, Zhaoyu Wang

Stochastic controllers are perceived as a promising solution for techno-economic operation of distribution networks having higher generation uncertainties at large penetration of renewables. These controllers are support…

continuous-controlContinuous Control

Know What You Know: Metacognitive Entropy Calibration for Verifiable RL Reasoning

2026-02-26 · Qiannian Zhao, Chen Yang, Jinhao Jing, Yunke Zhang 외 arxiv

Large reasoning models (LRMs) have emerged as a powerful paradigm for solving complex real-world tasks. In practice, these models are predominantly trained via Reinforcement Learning with Verifiable Rewards (RLVR), yet m…

Reinforcement LearningQuestion Answering

Sample-Adaptive Latent Rewards for Uncertainty-Guided Diffusion Post-Training

2026-08-06 · Rui Li, Yuanzhi Liang, Ke Hao, Ziqiao Weng 외 arxiv

Latent reward models can supervise visual diffusion models without decoding intermediate states into pixel space. This makes alignment with human preferences more efficient. However, existing latent reward models output …

Uncertainty-Aware Reward Modeling for Stable RLHF

2026-06-18 · Licheng Pan, Haocheng Yang, Haoxuan Li, Yichen Sun 외 arxiv

Reinforcement learning from human feedback (RLHF) aligns large language models by training reward models on preference data and optimizing policies to maximize predicted rewards. However, this pipeline faces two fundamen…

Reinforcement Learning