https://arxiv.org/abs/2106.00958 A Generalizable Approach to Learning Optimizers A core issue with learning to optimize neural networks has been the lack of generalization to real world problems. To address this, we describe a system designed from a generalization-first perspective, learning to update optimizer hyperparameters instead arxiv.org A core issue with learning to optimize neural netwo..

https://arxiv.org/pdf/2101.03958.pdf 0. Why Designing Reinforcement Learning Algorithms Are Important? "Designing new deep reinforcement learning algorithms that can efficiently solve across a wide variety of problems generally requires a tremendous amount of manual effort" -Evolving Reinforcement Learning Algorithms- 1. Designing Reinforcement Learning algorithms Deep Reinforcement Learning is ..

https://arxiv.org/abs/2007.14430 0. TD error and bootstrapping in reinforcement learning Munchen Reinforcement Learning (M-RL) is actually a really simple idea. Bootstrapping is a core idea in reinforcement learning, especially in learning q-functions with a temporal difference error. for example, we don't know the optimal q function at t+1, but the agent could use it as a learning target. we re..

https://arxiv.org/abs/2012.11989 Self-Imitation Advantage Learning Self-imitation learning is a Reinforcement Learning (RL) method that encourages actions whose returns were higher than expected, which helps in hard exploration and sparse reward problems. It was shown to improve the performance of on-policy actor-critic m arxiv.org 1. Self imitation reinforcement learning Self-imitation learning..