相关论文: How RL Agents Behave When Their Actions Are Modifi…

The problem of reinforcement learning is considered where the environment or the model undergoes a change. An algorithm is proposed that an agent can apply in such a problem to achieve the optimal long-time discounted reward. The algorithm…

A Markov Decision Process (MDP) is a popular model for reinforcement learning. However, its commonly used assumption of stationary dynamics and rewards is too stringent and fails to hold in adversarial, nonstationary, or multi-agent…

Many important behavior changes are frictionful; they require individuals to expend effort over a long period with little immediate gratification. Here, an artificial intelligence (AI) agent can provide personalized interventions to help…

Markov Decision Processes (MDPs), the mathematical framework underlying most algorithms in Reinforcement Learning (RL), are often used in a way that wrongfully assumes that the state of an agent's environment does not change during action…

Human behaviors are regularized by a variety of norms or regulations, either to maintain orders or to enhance social welfare. If artificially intelligent (AI) agents make decisions on behalf of human beings, we would hope they can also…

Inverse Reinforcement Learning (IRL) describes the problem of learning an unknown reward function of a Markov Decision Process (MDP) from observed behavior of an agent. Since the agent's behavior originates in its policy and MDP policies…

We consider the problem of learning to behave optimally in a Markov Decision Process when a reward function is not specified, but instead we have access to a set of demonstrators of varying performance. We assume the demonstrators are…

Reinforcement learning algorithms are typically designed for generic Markov Decision Processes (MDPs), where any state-action pair can lead to an arbitrary transition distribution. In many practical systems, however, only a subset of the…

We address the problem of reinforcement learning in which observations may exhibit an arbitrary form of stochastic dependence on past observations and actions, i.e. environments more general than (PO)MDPs. The task for an agent is to attain…

No real-world reward function is perfect. Sensory errors and software bugs may result in RL agents observing higher (or lower) rewards than they should. For example, a reinforcement learning agent may prefer states where a sensory error…

Reinforcement learning (RL) typically models the interaction between the agent and environment as a Markov decision process (MDP), where the rewards that guide the agent's behavior are always observable. However, in many real-world…

In order to satisfy safety conditions, an agent may be constrained from acting freely. A safe controller can be designed a priori if an environment is well understood, but not when learning is employed. In particular, reinforcement learned…

In practical applications, we can rarely assume full observability of a system's environment, despite such knowledge being important for determining a reactive control system's precise interaction with its environment. Therefore, we propose…

When developing reinforcement learning agents, the standard approach is to train an agent to converge to a fixed policy that is as close to optimal as possible for a single fixed reward function. If different agent behaviour is required in…

Developments in reinforcement learning (RL) have allowed algorithms to achieve impressive performance in highly complex, but largely static problems. In contrast, biological learning seems to value efficiency of adaptation to a…

In machine learning, meta-learning methods aim for fast adaptability to unknown tasks using prior knowledge. Model-based meta-reinforcement learning combines reinforcement learning via world models with Meta Reinforcement Learning (MRL) for…

Reinforcement learning algorithms describe how an agent can learn an optimal action policy in a sequential decision process, through repeated experience. In a given environment, the agent policy provides him some running and terminal…

Deep Reinforcement Learning (RL) is successful in solving many complex Markov Decision Processes (MDPs) problems. However, agents often face unanticipated environmental changes after deployment in the real world. These changes are often…

Reinforcement learning refers to a group of methods from artificial intelligence where an agent performs learning through trial and error. It differs from supervised learning, since reinforcement learning requires no explicit labels;…

Autonomous driving is a multi-agent setting where the host vehicle must apply sophisticated negotiation skills with other road users when overtaking, giving way, merging, taking left and right turns and while pushing ahead in unstructured…