Regulating Reward Training by Means of Certainty Prediction in a Neural Network-Implemented Pong Game
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.
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
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
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 ControlKnow What You Know: Metacognitive Entropy Calibration for Verifiable RL Reasoning
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 AnsweringSample-Adaptive Latent Rewards for Uncertainty-Guided Diffusion Post-Training
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
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