Related papers: Belief States for Cooperative Multi-Agent Reinforc…
Learning auxiliary tasks, such as multiple predictions about the world, can provide many benefits to reinforcement learning systems. A variety of off-policy learning algorithms have been developed to learn such predictions, but as yet there…
Model-based next state prediction and state value prediction are slow to converge. To address these challenges, we do the following: i) Instead of a neural network, we do model-based planning using a parallel memory retrieval system (which…
Learning a compact representation of history is critical for planning and generalization in partially observable environments. While meta-reinforcement learning (RL) agents can attain near Bayes-optimal policies, they often fail to learn…
Reinforcement learning has been shown to be highly successful at many challenging tasks. However, success heavily relies on well-shaped rewards. Intrinsically motivated RL attempts to remove this constraint by defining an intrinsic reward…
This paper extends the framework of partially observable Markov decision processes (POMDPs) to multi-agent settings by incorporating the notion of agent models into the state space. Agents maintain beliefs over physical states of the…
Most of the works on planning and learning, e.g., planning by (model based) reinforcement learning, are based on two main assumptions: (i) the set of states of the planning domain is fixed; (ii) the mapping between the observations from the…
State resetting is a fundamental but often overlooked capability of simulators. It supports sample-based planning by allowing resets to previously encountered simulation states, and enables calibration of simulators using real data by…
While humans and animals learn incrementally during their lifetimes and exploit their experience to solve new tasks, standard deep reinforcement learning methods specialize to solve only one task at a time. As a result, the information they…
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…
This paper extends the reinforcement learning ideas into the multi-agents system, which is far more complicated than the previously studied single-agent system. We studied two different multi-agents systems. One is the fully-connected…
Passive observational data, such as human videos, is abundant and rich in information, yet remains largely untapped by current RL methods. Perhaps surprisingly, we show that passive data, despite not having reward or action labels, can…
Reinforcement learning (RL) algorithms aim to learn optimal decisions in unknown environments through experience of taking actions and observing the rewards gained. In some cases, the environment is not influenced by the actions of the RL…
Choosing an appropriate representation of the environment for the underlying decision-making process of the reinforcement learning agent is not always straightforward. The state representation should be inclusive enough to allow the agent…
Reinforcement learning (RL) is well known for requiring large amounts of data in order for RL agents to learn to perform complex tasks. Recent progress in model-based RL allows agents to be much more data-efficient, as it enables them to…
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…
Multiagent reinforcement learning, as a prominent intelligent paradigm, enables collaborative decision-making within complex systems. However, existing approaches often rely on explicit action exchange between agents to evaluate action…
We consider model-based reinforcement learning (MBRL) in 2-agent, high-fidelity continuous control problems -- an important domain for robots interacting with other agents in the same workspace. For non-trivial dynamical systems, MBRL…
The increasing adoption of Reinforcement Learning in safety-critical systems domains such as autonomous vehicles, health, and aviation raises the need for ensuring their safety. Existing safety mechanisms such as adversarial training,…
Human guidance is often desired in reinforcement learning to improve the performance of the learning agent. However, human insights are often mere opinions and educated guesses rather than well-formulated arguments. While opinions are…
In reinforcement learning algorithms, leveraging multiple views of the environment can improve the learning of complicated policies. In multi-view environments, due to the fact that the views may frequently suffer from partial…