Related papers: One Policy to Control Them All: Shared Modular Pol…
The effects of policy sharing between agents in a multi-agent dynamical system has not been studied extensively. I simulate a system of agents optimizing the same task using reinforcement learning, to study the effects of different…
In recent years, reinforcement learning and imitation learning have shown great potential for controlling humanoid robots' motion. However, these methods typically create simulation environments and rewards for specific tasks, resulting in…
This paper presents LEMURS, an algorithm for learning scalable multi-robot control policies from cooperative task demonstrations. We propose a port-Hamiltonian description of the multi-robot system to exploit universal physical constraints…
Neuroscientific theory suggests that dopaminergic neurons broadcast global reward prediction errors to large areas of the brain influencing the synaptic plasticity of the neurons in those regions. We build on this theory to propose a…
The flocking motion control is concerned with managing the possible conflicts between local and team objectives of multi-agent systems. The overall control process guides the agents while monitoring the flock-cohesiveness and localization.…
This paper presents a hierarchical framework for Deep Reinforcement Learning that acquires motor skills for a variety of push recovery and balancing behaviors, i.e., ankle, hip, foot tilting, and stepping strategies. The policy is trained…
To perform manipulation tasks in the real world, robots need to operate on objects with various shapes, sizes and without access to geometric models. It is often unfeasible to train monolithic neural network policies across such large…
Deploying a safe mobile robot policy in scenarios with human pedestrians is challenging due to their unpredictable movements. Current Reinforcement Learning-based motion planners rely on a single policy to simulate pedestrian movements and…
In many reinforcement learning tasks, the goal is to learn a policy to manipulate an agent, whose design is fixed, to maximize some notion of cumulative reward. The design of the agent's physical structure is rarely optimized for the task…
Learned locomotion policies can rapidly adapt to diverse environments similar to those experienced during training but lack a mechanism for fast tuning when they fail in an out-of-distribution test environment. This necessitates a slow and…
Advances in multi-agent reinforcement learning (MARL) enable sequential decision making for a range of exciting multi-agent applications such as cooperative AI and autonomous driving. Explaining agent decisions is crucial for improving…
Human-AI shared control allows human to interact and collaborate with AI to accomplish control tasks in complex environments. Previous Reinforcement Learning (RL) methods attempt the goal-conditioned design to achieve human-controllable…
Learning cooperative multi-agent policies directly from high-dimensional, multimodal sensory inputs like pixels and audio (from pixels) is notoriously sample-inefficient. Model-free Multi-Agent Reinforcement Learning (MARL) algorithms…
Deep reinforcement learning produces robust locomotion policies for legged robots over challenging terrains. To date, few studies have leveraged model-based methods to combine these locomotion skills with the precise control of…
Cooperative multi-agent reinforcement learning (MARL) has achieved significant results, most notably by leveraging the representation-learning abilities of deep neural networks. However, large centralized approaches quickly become…
Many studies have applied reinforcement learning to train a dialog policy and show great promise these years. One common approach is to employ a user simulator to obtain a large number of simulated user experiences for reinforcement…
We consider the problem of using multiple agents to harvest data from a collection of sensor nodes (targets) scattered across a two-dimensional environment. These targets transmit their data to the agents that move in the space above them,…
In complex systems, we often observe complex global behavior emerge from a collection of agents interacting with each other in their environment, with each individual agent acting only on locally available information, without knowing the…
Model-free reinforcement learning has recently been shown to be effective at learning navigation policies from complex image input. However, these algorithms tend to require large amounts of interaction with the environment, which can be…
Reinforcement learning is an emerging approach to control dynamical systems for which classical approaches are difficult to apply. However, trained agents may not generalize against the variations of system parameters. This paper presents…