Related papers: VA-learning as a more efficient alternative to Q-l…
Current reinforcement learning algorithms train an agent using forward-generated trajectories, which provide little guidance so that the agent can explore as much as possible. While realizing the value of reinforcement learning results from…
Policy evaluation is a core component of many reinforcement learning (RL) algorithms and a critical tool for ensuring safe deployment of RL policies. However, existing policy evaluation methods often suffer from high variance or bias. To…
Deep reinforcement learning has been shown to be a powerful framework for learning policies from complex high-dimensional sensory inputs to actions in complex tasks, such as the Atari domain. In this paper, we explore output representation…
Recent breakthroughs in Go play and strategic games have witnessed the great potential of reinforcement learning in intelligently scheduling in uncertain environment, but some bottlenecks are also encountered when we generalize this…
While a number of existing approaches for building foundation model agents rely on prompting or fine-tuning with human demonstrations, it is not sufficient in dynamic environments (e.g., mobile device control). On-policy reinforcement…
We evaluate the use of original game curricula supported by the Atari 2600 console as a heterogeneous transfer benchmark for deep reinforcement learning agents. Game designers created curricula using combinations of several discrete…
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…
Policy gradient is an efficient technique for improving a policy in a reinforcement learning setting. However, vanilla online variants are on-policy only and not able to take advantage of off-policy data. In this paper we describe a new…
Learning an effective representation for high-dimensional data is a challenging problem in reinforcement learning (RL). Deep reinforcement learning (DRL) such as Deep Q networks (DQN) achieves remarkable success in computer games by…
In many real world applications, reinforcement learning agents have to optimize multiple objectives while following certain rules or satisfying a list of constraints. Classical methods based on reward shaping, i.e. a weighted combination of…
Off-policy reinforcement learning (RL) using a fixed offline dataset of logged interactions is an important consideration in real world applications. This paper studies offline RL using the DQN replay dataset comprising the entire replay…
Reinforcement learning holds the promise of enabling autonomous robots to learn large repertoires of behavioral skills with minimal human intervention. However, robotic applications of reinforcement learning often compromise the autonomy of…
Deep reinforcement learning agents have achieved state-of-the-art results by directly maximising cumulative reward. However, environments contain a much wider variety of possible training signals. In this paper, we introduce an agent that…
While deep reinforcement learning has successfully solved many challenging control tasks, its real-world applicability has been limited by the inability to ensure the safety of learned policies. We propose an approach to verifiable…
We present a new algorithm that significantly improves the efficiency of exploration for deep Q-learning agents in dialogue systems. Our agents explore via Thompson sampling, drawing Monte Carlo samples from a Bayes-by-Backprop neural…
In this paper, we propose a novel Reinforcement Learning approach for solving the Active Information Acquisition problem, which requires an agent to choose a sequence of actions in order to acquire information about a process of interest…
We methodologically address the problem of Q-value overestimation in deep reinforcement learning to handle high-dimensional state spaces efficiently. By adapting concepts from information theory, we introduce an intrinsic penalty signal…
Potential Based Reward Shaping combined with a potential function based on appropriately defined abstract knowledge has been shown to significantly improve learning speed in Reinforcement Learning. MultiGrid Reinforcement Learning (MRL) has…
We present a new algorithm that significantly improves the efficiency of exploration for deep Q-learning agents in dialogue systems. Our agents explore via Thompson sampling, drawing Monte Carlo samples from a Bayes-by-Backprop neural…
To accumulate knowledge and improve its policy of behaviour, a reinforcement learning agent can learn `off-policy' about policies that differ from the policy used to generate its experience. This is important to learn counterfactuals, or…