Related papers: Simplifying Deep Temporal Difference Learning
Reinforcement learning is able to solve complex sequential decision-making tasks but is currently limited by sample efficiency and required computation. To improve sample efficiency, recent work focuses on model-based RL which interleaves…
In this paper, we address two key challenges in deep reinforcement learning setting, sample inefficiency and slow learning, with a dual NN-driven learning approach. In the proposed approach, we use two deep NNs with independent…
Training a deep neural network to maximize a target objective has become the standard recipe for successful machine learning over the last decade. These networks can be optimized with supervised learning, if the target objective is…
High update-to-data (UTD) ratio algorithms in reinforcement learning (RL) improve sample efficiency but incur high computational costs, limiting real-world scalability. We propose Offline Stabilization Phases for Efficient Q-Learning…
In this paper, we build on advances introduced by the Deep Q-Networks (DQN) approach to extend the multi-objective tabular Reinforcement Learning (RL) algorithm W-learning to large state spaces. W-learning algorithm can naturally solve the…
Offline reinforcement learning enables learning from a fixed dataset, without further interactions with the environment. The lack of environmental interactions makes the policy training vulnerable to state-action pairs far from the training…
Policy iteration is one of the classical frameworks of reinforcement learning, which requires a known initial stabilizing control. However, finding the initial stabilizing control depends on the known system model. To relax this requirement…
Despite remarkable successes, Deep Reinforcement Learning (DRL) is not robust to hyperparameterization, implementation details, or small environment changes (Henderson et al. 2017, Zhang et al. 2018). Overcoming such sensitivity is key to…
One of the major challenges in Deep Reinforcement Learning for control is the need for extensive training to learn the policy. Motivated by this, we present the design of the Control-Tutored Deep Q-Networks (CT-DQN) algorithm, a Deep…
Tennis strategy optimization is a challenging sequential decision-making problem involving hierarchical scoring, stochastic outcomes, long-horizon credit assignment, physical fatigue, and adaptation to opponent skill. I present a…
Policies for complex visual tasks have been successfully learned with deep reinforcement learning, using an approach called deep Q-networks (DQN), but relatively large (task-specific) networks and extensive training are needed to achieve…
Leveraging many sources of offline robot data requires grappling with the heterogeneity of such data. In this paper, we focus on one particular aspect of heterogeneity: learning from offline data collected at different control frequencies.…
Routing in multi-hop wireless networks is a complex problem, especially in heterogeneous networks where multiple wireless communication technologies coexist. Reinforcement learning (RL) methods, such as Q-learning, have been introduced for…
Deep Reinforcement Learning (RL) demonstrates excellent performance on tasks that can be solved by trained policy. It plays a dominant role among cutting-edge machine learning approaches using multi-layer Neural networks (NNs). At the same…
Integral to recent successes in deep reinforcement learning has been a class of temporal difference methods that use infrequently updated target values for policy evaluation in a Markov Decision Process. Yet a complete theoretical…
Offline reinforcement learning requires reconciling two conflicting aims: learning a policy that improves over the behavior policy that collected the dataset, while at the same time minimizing the deviation from the behavior policy so as to…
Double Q-learning is a classical control algorithm that mitigates the maximization bias of Q-learning. To do so, it explicitly trains two independent action-value functions and uses them to decouple action-selection and action-evaluation…
We present a novel definition of the reinforcement learning state, actions and reward function that allows a deep Q-network (DQN) to learn to control an optimization hyperparameter. Using Q-learning with experience replay, we train two DQNs…
Relative temporal-difference (TD) learning was introduced to mitigate the slow convergence of TD methods when the discount factor approaches one by subtracting a baseline from the temporal-difference update. While this idea has been studied…
The field of Offline Reinforcement Learning (RL) aims to derive effective policies from pre-collected datasets without active environment interaction. While traditional offline RL algorithms like Conservative Q-Learning (CQL) and Implicit…