相关论文: Evaluating Agents without Rewards

Algorithmic collusion has emerged as a central question in AI: Will the interaction between different AI agents deployed in markets lead to collusion? More generally, understanding how emergent behavior, be it a cartel or market dominance…

The correct specification of reward models is a well-known challenge in reinforcement learning. Hand-crafted reward functions often lead to inefficient or suboptimal policies and may not be aligned with user values. Reinforcement learning…

Text-based games are a popular testbed for language-based reinforcement learning (RL). In previous work, deep Q-learning is commonly used as the learning agent. Q-learning algorithms are challenging to apply to complex real-world domains…

"Intrinsic motivation" refers to the capacity for intelligent systems to be motivated endogenously, i.e. by features of agential architecture itself rather than by learned associations between action and reward. This paper views active…

Intrinsic motivations are receiving increasing attention, i.e. behavioral incentives that are not engineered, but emerge from the interaction of an agent with its surroundings. In this work we study the emergence of behaviors driven by one…

We argue that 3-D first-person video games are a challenging environment for real-time multi-modal reasoning. We first describe our dataset of human game-play, collected across a large variety of 3-D first-person games, which is both…

For most reinforcement learning approaches, the learning is performed by maximizing an accumulative reward that is expectedly and manually defined for specific tasks. However, in real world, rewards are emergent phenomena from the complex…

Deep reinforcement learning (RL) policies, although optimal in terms of task rewards, may not align with the personal preferences of human users. To ensure this alignment, a naive solution would be to retrain the agent using a reward…

We pose an active perception problem where an autonomous agent actively interacts with a second agent with potentially adversarial behaviors. Given the uncertainty in the intent of the other agent, the objective is to collect further…

Exploration is a difficult challenge in reinforcement learning and even recent state-of-the art curiosity-based methods rely on the simple epsilon-greedy strategy to generate novelty. We argue that pure random walks do not succeed to…

Critical sectors of human society are progressing toward the adoption of powerful artificial intelligence (AI) agents, which are trained individually on behalf of self-interested principals but deployed in a shared environment. Short of…

Infants are experts at playing, with an amazing ability to generate novel structured behaviors in unstructured environments that lack clear extrinsic reward signals. We seek to mathematically formalize these abilities using a neural network…

Sample inefficiency of deep reinforcement learning methods is a major obstacle for their use in real-world applications. In this work, we show how human demonstrations can improve final performance of agents on the Minecraft minigame…

Financial markets investors are involved in many games -- they must interact with other agents to achieve their goals. Among them are those directly connected with their activity on markets but one cannot neglect other aspects that…

Efficient exploration in multi-agent reinforcement learning (MARL) is a challenging problem when receiving only a team reward, especially in environments with sparse rewards. A powerful method to mitigate this issue involves crafting dense…

We seek to align agent behavior with a user's objectives in a reinforcement learning setting with unknown dynamics, an unknown reward function, and unknown unsafe states. The user knows the rewards and unsafe states, but querying the user…

Extrinsic rewards can effectively guide reinforcement learning (RL) agents in specific tasks. However, extrinsic rewards frequently fall short in complex environments due to the significant human effort needed for their design and…

Exploration is essential in reinforcement learning as an agent relies on trial and error to learn an optimal policy. However, when rewards are sparse, naive exploration strategies, like noise injection, are often insufficient. Intrinsic…

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…

Intrinsic motivation enables reinforcement learning (RL) agents to explore when rewards are very sparse, where traditional exploration heuristics such as Boltzmann or e-greedy would typically fail. However, intrinsic exploration is…