Related papers: Implicit Quantile Networks for Distributional Rein…
The ability to learn continually is essential in a complex and changing world. In this paper, we characterize the behavior of canonical value-based deep reinforcement learning (RL) approaches under varying degrees of non-stationarity. In…
Model-free learning for multi-agent stochastic games is an active area of research. Existing reinforcement learning algorithms, however, are often restricted to zero-sum games, and are applicable only in small state-action spaces or other…
Reinforcement learning agents in complex game environments often suffer from sparse rewards, training instability, and poor sample efficiency. This paper presents a hybrid training approach that combines offline imitation learning with…
Prioritized experience replay (PER) samples important transitions, rather than uniformly, to improve the performance of a deep reinforcement learning agent. We claim that such prioritization has to be balanced with sample diversity for…
Distributional reinforcement learning algorithms have attempted to utilize estimated uncertainty for exploration, such as optimism in the face of uncertainty. However, using the estimated variance for optimistic exploration may cause biased…
In this paper, we provide the details of implementing various reinforcement learning (RL) algorithms for controlling a Cart-Pole system. In particular, we describe various RL concepts such as Q-learning, Deep Q Networks (DQN), Double DQN,…
We analyze independent policy-gradient (PG) learning in $N$-player linear-quadratic (LQ) stochastic differential games. Each player employs a distributed policy that depends only on its own state and updates the policy independently using…
Real-world reinforcement learning tasks often involve some form of partial observability where the observations only give a partial or noisy view of the true state of the world. Such tasks typically require some form of memory, where the…
We consider a dynamic multichannel access problem, where multiple correlated channels follow an unknown joint Markov model. A user at each time slot selects a channel to transmit data and receives a reward based on the success or failure of…
We introduce autoregressive implicit quantile networks (AIQN), a fundamentally different approach to generative modeling than those commonly used, that implicitly captures the distribution using quantile regression. AIQN is able to achieve…
Effective reinforcement learning requires a proper balance of exploration and exploitation defined by the dispersion of action distribution. However, this balance depends on the task, the current stage of the learning process, and the…
Feature attribution has been a foundational building block for explaining the input feature importance in supervised learning with Deep Neural Network (DNNs), but face new challenges when applied to deep Reinforcement Learning (RL).We…
Deep reinforcement learning has shown its success in game playing. However, 2.5D fighting games would be a challenging task to handle due to ambiguity in visual appearances like height or depth of the characters. Moreover, actions in such…
In this work, we propose and evaluate a new reinforcement learning method, COMPact Experience Replay (COMPER), which uses temporal difference learning with predicted target values based on recurrence over sets of similar transitions, and a…
Network slicing promises to provision diversified services with distinct requirements in one infrastructure. Deep reinforcement learning (e.g., deep $\mathcal{Q}$-learning, DQL) is assumed to be an appropriate algorithm to solve the…
Dynamic resource allocation in O-RAN is critical for managing the conflicting QoS requirements of 6G network slices. Conventional reinforcement learning agents often fail in this domain, as their unimodal policy structures cannot model the…
The deep Q-network (DQN) and return-based reinforcement learning are two promising algorithms proposed in recent years. DQN brings advances to complex sequential decision problems, while return-based algorithms have advantages in making use…
Humans can flexibly generalize knowledge across domains by leveraging structured relational representations. While prior research has shown how such representations support analogical reasoning, less is known about how they are recruited to…
Deep reinforcement learning (DRL) has demonstrated impressive performance in various gaming simulators and real-world applications. In practice, however, a DRL agent may receive faulty observation by abrupt interferences such as black-out,…
Recurrent neural networks (RNNs) are an effective representation of control policies for a wide range of reinforcement and imitation learning problems. RNN policies, however, are particularly difficult to explain, understand, and analyze…