13 accepted papers
In continual RL we want agents capable of never-ending learning, and yet our evaluation methodologies do not reflect this. The standard practice in RL is to assume unfettered access to the deployment environment for the full lifetime of the agent. For example, agent designers select the best perform…
The performance of modern reinforcement learning algorithms critically relies on tuning ever increasing numbers of hyperparameters. Often, small changes in a hyperparameter can lead to drastic changes in performance, and different environments require very different hyperparameter settings to achiev…
In this position paper, we argue that application-driven research has been systemically under-valued in the machine learning community. As applications of machine learning proliferate, innovative algorithms inspired by specific real-world challenges have become increasingly important. Such work offe…
Novel reinforcement learning algorithms, or improvements on existing ones, are commonly justified by evaluating their performance on benchmark environments and are compared to an ever-changing set of standard algorithms. However, despite numerous calls for improvements, experimental practices contin…
Recurrent Neural Networks (RNNs) are used to learn representations in partially observable environments. For agents that learn online and continually interact with the environment, it is desirable to train RNNs with real-time recurrent learning (RTRL); unfortunately, RTRL is prohibitively expensive…
To achieve the ambitious goals of artificial intelligence, reinforcement learning must include planning with a model of the world that is abstract in state and time. Deep learning has made progress with state abstraction, but temporal abstraction has rarely been used, despite extensively developed t…
Many policy gradient methods are variants of Actor-Critic (AC), where a value function (critic) is learned to facilitate updating the parameterized policy (actor). The update to the actor involves a log-likelihood update weighted by the action-values, with the addition of entropy regularization for…
Reinforcement learning (RL) agents can leverage batches of previously collected data to extract a reasonable control policy. An emerging issue in this offline RL setting, however, is that the bootstrapping update underlying many of our methods suffers from insufficient action-coverage: standard max…
Off-policy sampling and experience replay are key for improving sample efficiency and scaling model-free temporal difference learning methods. When combined with function approximation, such as neural networks, this combination is known as the deadly triad and is potentially unstable. Recently, it h…
Off-policy learning allows us to learn about possible policies of behavior from experience generated by a different behavior policy. Temporal difference (TD) learning algorithms can become unstable when combined with function approximation and off-policy sampling—this is known as the “deadly triad”.…
It is still common to use Q-learning and temporal difference (TD) learning{—}even though they have divergence issues and sound Gradient TD alternatives exist{—}because divergence seems rare and they typically perform well. However, recent work with large neural network learning systems reveals that…
Recurrent neural networks (RNNs) allow an agent to construct a state-representation from a stream of experience, which is essential in partially observable problems. However, there are two primary issues one must overcome when training an RNN: the sensitivity of the learning algorithm's performance…
Directed exploration strategies for reinforcement learning are critical for learning an optimal policy in a minimal number of interactions with the environment. Many algorithms use optimism to direct exploration, either through visitation estimates or upper confidence bounds, as opposed to data-inef…