Related papers: Fast and Data-Efficient Training of Rainbow: an Ex…
Rainbow Deep Q-Network (DQN) demonstrated combining multiple independent enhancements could significantly boost a reinforcement learning (RL) agent's performance. In this paper, we present "Beyond The Rainbow" (BTR), a novel algorithm that…
Consistent and reproducible evaluation of Deep Reinforcement Learning (DRL) is not straightforward. In the Arcade Learning Environment (ALE), small changes in environment parameters such as stochasticity or the maximum allowed play time can…
Since the introduction of DQN, a vast majority of reinforcement learning research has focused on reinforcement learning with deep neural networks as function approximators. New methods are typically evaluated on a set of environments that…
The deep reinforcement learning community has made several independent improvements to the DQN algorithm. However, it is unclear which of these extensions are complementary and can be fruitfully combined. This paper examines six extensions…
Data efficiency is a key challenge for deep reinforcement learning. We address this problem by using unlabeled data to pretrain an encoder which is then finetuned on a small amount of task-specific data. To encourage learning…
Reinforcement learning (RL) has seen great advancements in the past few years. Nevertheless, the consensus among the RL community is that currently used methods, despite all their benefits, suffer from extreme data inefficiency, especially…
Deep reinforcement learning (RL) has achieved many recent successes, yet experiment turn-around time remains a key bottleneck in research and in practice. We investigate how to optimize existing deep RL algorithms for modern computers,…
Playing two-player games using reinforcement learning and self-play can be challenging due to the complexity of two-player environments and the possible instability in the training process. We propose that a reinforcement learning algorithm…
While reinforcement learning agents can achieve superhuman performance in many complex tasks, they typically do not become more computationally efficient as they improve. In contrast, humans gradually require less cognitive effort as they…
Deep reinforcement learning algorithms often use two networks for value function optimization: an online network, and a target network that tracks the online network with some delay. Using two separate networks enables the agent to hedge…
Reinforcement learning has achieved great success in many applications. However, sample efficiency remains a key challenge, with prominent methods requiring millions (or even billions) of environment steps to train. Recently, there has been…
Deep reinforcement learning (DeepRL) agents surpass human-level performance in many tasks. However, the direct mapping from states to actions makes it hard to interpret the rationale behind the decision-making of the agents. In contrast to…
Recent progress in Reinforcement Learning (RL), fueled by its combination, with Deep Learning has enabled impressive results in learning to interact with complex virtual environments, yet real-world applications of RL are still scarce. A…
We propose a novel training algorithm for reinforcement learning which combines the strength of deep Q-learning with a constrained optimization approach to tighten optimality and encourage faster reward propagation. Our novel technique…
Continual learning is a realistic learning scenario for AI models. Prevalent scenario of continual learning, however, assumes disjoint sets of classes as tasks and is less realistic rather artificial. Instead, we focus on 'blurry' task…
Training large-scale deep learning models has become a key challenge for the scientific community and industry. While the massive use of GPUs can significantly speed up training times, this approach has a negative impact on efficiency. In…
Sampled environment transitions are a critical input to deep reinforcement learning (DRL) algorithms. Current DRL benchmarks often allow for the cheap and easy generation of large amounts of samples such that perceived progress in DRL does…
High sample complexity has long been a challenge for RL. On the other hand, humans learn to perform tasks not only from interaction or demonstrations, but also by reading unstructured text documents, e.g., instruction manuals. Instruction…
Deep reinforcement learning (RL) agents achieve impressive results in a wide variety of tasks, but they lack zero-shot adaptation capabilities. While most robustness evaluations focus on tasks complexifications, for which human also…
Deep reinforcement learning (deep RL) has achieved superior performance in complex sequential tasks by using deep neural networks as function approximators to learn directly from raw input images. However, learning directly from raw images…