Related papers: Double Prioritized State Recycled Experience Repla…
Reinforcement learning agents learn by encouraging behaviours which maximize their total reward, usually provided by the environment. In many environments, however, the reward is provided after a series of actions rather than each single…
This paper presents an actor-critic deep reinforcement learning agent with experience replay that is stable, sample efficient, and performs remarkably well on challenging environments, including the discrete 57-game Atari domain and several…
Recent advance in deep offline reinforcement learning (RL) has made it possible to train strong robotic agents from offline datasets. However, depending on the quality of the trained agents and the application being considered, it is often…
Background: Deep Deterministic Policy Gradient-based reinforcement learning algorithms utilize Actor-Critic architectures, where both networks are typically trained using identical batches of replayed transitions. However, the learning…
In order perform a large variety of tasks and to achieve human-level performance in complex real-world environments, Artificial Intelligence (AI) Agents must be able to learn from their past experiences and gain both knowledge and an…
Experience replay enables reinforcement learning agents to memorize and reuse past experiences, just as humans replay memories for the situation at hand. Contemporary off-policy algorithms either replay past experiences uniformly or utilize…
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…
Given the inherent non-stationarity prevalent in real-world applications, continual Reinforcement Learning (RL) aims to equip the agent with the capability to address a series of sequentially presented decision-making tasks. Within this…
Deep Q Network (DQN) has several limitations when applied in planning a path in environment with a number of dilemmas according to our experiment. The reward function may be hard to model, and successful experience transitions are difficult…
On-policy deep reinforcement learning algorithms have low data utilization and require significant experience for policy improvement. This paper proposes a proximal policy optimization algorithm with prioritized trajectory replay (PTR-PPO)…
In this work, we build on recent advances in distributional reinforcement learning to give a generally applicable, flexible, and state-of-the-art distributional variant of DQN. We achieve this by using quantile regression to approximate the…
We employ the Deep Q-Learning algorithm with Experience Replay to train an agent capable of achieving a high-level of play in the L-Game while self-learning from low-dimensional states. We also employ variable batch size for training in…
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…
Recent times have witnessed sharp improvements in reinforcement learning tasks using deep reinforcement learning techniques like Deep Q Networks, Policy Gradients, Actor Critic methods which are based on deep learning based models and…
Recent advances in off-policy deep reinforcement learning (RL) have led to impressive success in complex tasks from visual observations. Experience replay improves sample-efficiency by reusing experiences from the past, and convolutional…
Deep reinforcement learning is a technique for solving problems in a variety of environments, ranging from Atari video games to stock trading. This method leverages deep neural network models to make decisions based on observations of a…
Agents must be able to adapt quickly as an environment changes. We find that existing model-based reinforcement learning agents are unable to do this well, in part because of how they use past experiences to train their world model. Here,…
Continual learning is the problem of learning new tasks or knowledge while protecting old knowledge and ideally generalizing from old experience to learn new tasks faster. Neural networks trained by stochastic gradient descent often degrade…
Transformers are neural network models that utilize multiple layers of self-attention heads and have exhibited enormous potential in natural language processing tasks. Meanwhile, there have been efforts to adapt transformers to visual tasks…
Building upon the recent success of deep reinforcement learning methods, we investigate the possibility of on-policy reinforcement learning improvement by reusing the data from several consecutive policies. On-policy methods bring many…