Related papers: Generalizing Multi-Step Inverse Models for Represe…

This paper presents a novel state representation for reward-free Markov decision processes. The idea is to learn, in a self-supervised manner, an embedding space where distances between pairs of embedded states correspond to the minimum…

In inverse reinforcement learning (IRL), a learning agent infers a reward function encoding the underlying task using demonstrations from experts. However, many existing IRL techniques make the often unrealistic assumption that the agent…

A common strategy in modern learning systems is to learn a representation that is useful for many tasks, a.k.a. representation learning. We study this strategy in the imitation learning setting for Markov decision processes (MDPs) where…

We are interested in enabling autonomous agents to learn and reason about systems with hidden states, such as locking mechanisms. We cast this problem as learning the parameters of a discrete Partially Observable Markov Decision Process…

We consider the problem of building a state representation model in a continual fashion. As the environment changes, the aim is to efficiently compress the sensory state's information without losing past knowledge. The learned features are…

Many real-world applications require an agent to make robust and deliberate decisions with multimodal information (e.g., robots with multi-sensory inputs). However, it is very challenging to train the agent via reinforcement learning (RL)…

To generalize across tasks, an agent should acquire knowledge from past tasks that facilitate adaptation and exploration in future tasks. We focus on the problem of in-context adaptation and exploration, where an agent only relies on…

Driving in a dynamic, multi-agent, and complex urban environment is a difficult task requiring a complex decision-making policy. The learning of such a policy requires a state representation that can encode the entire environment. Mid-level…

Partially Observable Markov Decision Processes (POMDPs) remain a core challenge in reinforcement learning due to incomplete state information. We address this by reformulating POMDPs as fully observable processes with fixed-length…

Planning plays an important role in the broad class of decision theory. Planning has drawn much attention in recent work in the robotics and sequential decision making areas. Recently, Reinforcement Learning (RL), as an agent-environment…

Agents trained via deep reinforcement learning (RL) routinely fail to generalize to unseen environments, even when these share the same underlying dynamics as the training levels. Understanding the generalization properties of RL is one of…

In this paper, we are interested in systems with multiple agents that wish to collaborate in order to accomplish a common task while a) agents have different information (decentralized information) and b) agents do not know the model of the…

We examine the problem of learning mappings from state to state, suitable for use in a model-based reinforcement-learning setting, that simultaneously generalize to novel states and can capture stochastic transitions. We show that currently…

We propose a novel Reinforcement Learning model for discrete environments, which is inherently interpretable and supports the discovery of deep subgoal hierarchies. In the model, an agent learns information about environment in the form of…

Policies for partially observed Markov decision processes can be efficiently learned by imitating policies for the corresponding fully observed Markov decision processes. Unfortunately, existing approaches for this kind of imitation…

We study the problem of decentralized constrained POMDPs in a team-setting where the multiple non-strategic agents have asymmetric information. Strong duality is established for the setting of infinite-horizon expected total discounted…

In reinforcement learning, state representations are used to tractably deal with large problem spaces. State representations serve both to approximate the value function with few parameters, but also to generalize to newly encountered…

Solving partially observable Markov decision processes (POMDPs) requires computing policies under imperfect state information. Despite recent advances, the scalability of existing POMDP solvers remains limited. Moreover, many settings…

Modern model-free reinforcement learning methods have recently demonstrated impressive results on a number of problems. However, complex domains like dexterous manipulation remain a challenge due to the high sample complexity. To address…

Decision analysis deals with modeling and enhancing decision processes. A principal challenge in improving behavior is in obtaining a transparent description of existing behavior in the first place. In this paper, we develop an expressive,…