Search Results for author:
Found 45 papers, 12 papers with code
Vision and Language Navigation in the Real World via Online Visual Language Mapping
Directly transferring SOTA navigation policies trained in simulation to the real world is challenging due to the visual domain gap and the absence of prior knowledge about unseen environments.
Multi-Agent Reinforcement Learning Based on Representational Communication for Large-Scale Traffic Signal Control
In this study, we propose a communication-based MARL framework for large-scale TSC.
On-Robot Bayesian Reinforcement Learning for POMDPs
Bayesian reinforcement learning (BRL), thanks to its sample efficiency and ability to exploit prior knowledge, is uniquely positioned as such a solution method.
Safe Deep Reinforcement Learning by Verifying Task-Level Properties
In this paper, we investigate an alternative approach that uses domain knowledge to quantify the risk in the proximity of such states by defining a violation metric.
Improving Deep Policy Gradients with Value Function Search
Deep Policy Gradient (PG) algorithms employ value networks to drive the learning of parameterized policies and reduce the variance of the gradient estimates.
Trajectory-Aware Eligibility Traces for Off-Policy Reinforcement Learning
Off-policy learning from multistep returns is crucial for sample-efficient reinforcement learning, but counteracting off-policy bias without exacerbating variance is challenging.
Leveraging Fully Observable Policies for Learning under Partial Observability
Reinforcement learning in partially observable domains is challenging due to the lack of observable state information.
Partially Observable Reinforcement Learning
reinforcement-learning
+1
Asynchronous Actor-Critic for Multi-Agent Reinforcement Learning
Synchronizing decisions across multiple agents in realistic settings is problematic since it requires agents to wait for other agents to terminate and communicate about termination reliably.
Deep Transformer Q-Networks for Partially Observable Reinforcement Learning
Such tasks typically require some form of memory, where the agent has access to multiple past observations, in order to perform well.
Partially Observable Reinforcement Learning
reinforcement-learning
+1
BADDr: Bayes-Adaptive Deep Dropout RL for POMDPs
Under this parameterization, in contrast to previous work, the belief over the state and dynamics is a more scalable inference problem.
A Deeper Understanding of State-Based Critics in Multi-Agent Reinforcement Learning
Centralized Training for Decentralized Execution, where training is done in a centralized offline fashion, has become a popular solution paradigm in Multi-Agent Reinforcement Learning.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Improving the Efficiency of Off-Policy Reinforcement Learning by Accounting for Past Decisions
Off-policy learning from multistep returns is crucial for sample-efficient reinforcement learning, particularly in the experience replay setting now commonly used with deep neural networks.
Virtual Replay Cache
Return caching is a recent strategy that enables efficient minibatch training with multistep estimators (e. g. the {\lambda}-return) for deep reinforcement learning.
Human-Level Control without Server-Grade Hardware
Deep Q-Network (DQN) marked a major milestone for reinforcement learning, demonstrating for the first time that human-level control policies could be learned directly from raw visual inputs via reward maximization.
Local Advantage Actor-Critic for Robust Multi-Agent Deep Reinforcement Learning
By using this local critic, each agent calculates a baseline to reduce variance on its policy gradient estimation, which results in an expected advantage action-value over other agents' choices that implicitly improves credit assignment.
Multi-agent Reinforcement Learning
Policy Gradient Methods
+2
Asynchronous Multi-Agent Actor-Critic with Macro-Actions
Many realistic multi-agent problems naturally require agents to be capable of performing asynchronously without waiting for other agents to terminate (e. g., multi-robot domains).
Investigating Alternatives to the Root Mean Square for Adaptive Gradient Methods
Adam is an adaptive gradient method that has experienced widespread adoption due to its fast and reliable training performance.
Reconciling Rewards with Predictive State Representations
We show that there is a mismatch between optimal POMDP policies and the optimal PSR policies derived from approximate rewards.
Hierarchical Robot Navigation in Novel Environments using Rough 2-D Maps
In this work, we propose an approach that leverages a rough 2-D map of the environment to navigate in novel environments without requiring further learning.
Unbiased Asymmetric Reinforcement Learning under Partial Observability
In partially observable reinforcement learning, offline training gives access to latent information which is not available during online training and/or execution, such as the system state.
Partially Observable Reinforcement Learning
reinforcement-learning
+1
End-to-end grasping policies for human-in-the-loop robots via deep reinforcement learning
State-of-the-art human-in-the-loop robot grasping is hugely suffered by Electromyography (EMG) inference robustness issues.
Decentralized Reinforcement Learning for Multi-Target Search and Detection by a Team of Drones
Targets search and detection encompasses a variety of decision problems such as coverage, surveillance, search, observing and pursuit-evasion along with others.
Stratified Experience Replay: Correcting Multiplicity Bias in Off-Policy Reinforcement Learning
Our theory prescribes a special non-uniform distribution to cancel this effect, and we propose a stratified sampling scheme to efficiently implement it.
Contrasting Centralized and Decentralized Critics in Multi-Agent Reinforcement Learning
Centralized Training for Decentralized Execution, where agents are trained offline using centralized information but execute in a decentralized manner online, has gained popularity in the multi-agent reinforcement learning community.
Safe Multi-Agent Reinforcement Learning via Shielding
Multi-agent reinforcement learning (MARL) has been increasingly used in a wide range of safety-critical applications, which require guaranteed safety (e. g., no unsafe states are ever visited) during the learning process. Unfortunately, current MARL methods do not have safety guarantees.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Belief-Grounded Networks for Accelerated Robot Learning under Partial Observability
Many important robotics problems are partially observable in the sense that a single visual or force-feedback measurement is insufficient to reconstruct the state.
Expectigrad: Fast Stochastic Optimization with Robust Convergence Properties
Many popular adaptive gradient methods such as Adam and RMSProp rely on an exponential moving average (EMA) to normalize their stepsizes.
Macro-Action-Based Deep Multi-Agent Reinforcement Learning
In real-world multi-robot systems, performing high-quality, collaborative behaviors requires robots to asynchronously reason about high-level action selection at varying time durations.
Reconciling λ-Returns with Experience Replay
Modern deep reinforcement learning methods have departed from the incremental learning required for eligibility traces, rendering the implementation of the λ-return difficult in this context.
Active Goal Recognition
We propose to combine goal recognition with other observer tasks in order to obtain \emph{active goal recognition} (AGR).
Learning Multi-Robot Decentralized Macro-Action-Based Policies via a Centralized Q-Net
In many real-world multi-robot tasks, high-quality solutions often require a team of robots to perform asynchronous actions under decentralized control.
Likelihood Quantile Networks for Coordinating Multi-Agent Reinforcement Learning
When multiple agents learn in a decentralized manner, the environment appears non-stationary from the perspective of an individual agent due to the exploration and learning of the other agents.
Bayesian Reinforcement Learning in Factored POMDPs
Bayesian approaches provide a principled solution to the exploration-exploitation trade-off in Reinforcement Learning.
Reconciling $λ$-Returns with Experience Replay
Modern deep reinforcement learning methods have departed from the incremental learning required for eligibility traces, rendering the implementation of the $\lambda$-return difficult in this context.
Learning in POMDPs with Monte Carlo Tree Search
The POMDP is a powerful framework for reasoning under outcome and information uncertainty, but constructing an accurate POMDP model is difficult.
Learning to Teach in Cooperative Multiagent Reinforcement Learning
The problem of teaching to improve agent learning has been investigated by prior works, but these approaches make assumptions that prevent application of teaching to general multiagent problems, or require domain expertise for problems they can apply to.
Near-Optimal Adversarial Policy Switching for Decentralized Asynchronous Multi-Agent Systems
The practicality of existing works addressing this challenge is limited to only small-scale synchronous decision-making scenarios or a single agent planning its best response against a single adversary with fixed, procedurally characterized strategies.
Learning for Multi-robot Cooperation in Partially Observable Stochastic Environments with Macro-actions
We implement two variants of multi-robot Search and Rescue (SAR) domains (with and without obstacles) on hardware to demonstrate the learned policies can effectively control a team of distributed robots to cooperate in a partially observable stochastic environment.
Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability
Many real-world tasks involve multiple agents with partial observability and limited communication.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Stick-Breaking Policy Learning in Dec-POMDPs
Expectation maximization (EM) has recently been shown to be an efficient algorithm for learning finite-state controllers (FSCs) in large decentralized POMDPs (Dec-POMDPs).
Decentralized Control of Partially Observable Markov Decision Processes using Belief Space Macro-actions
To allow for a high-level representation that is natural for multi-robot problems and scalable to large discrete and continuous problems, this paper extends the Dec-POMDP model to the decentralized partially observable semi-Markov decision process (Dec-POSMDP).
Scalable Planning and Learning for Multiagent POMDPs: Extended Version
Online, sample-based planning algorithms for POMDPs have shown great promise in scaling to problems with large state spaces, but they become intractable for large action and observation spaces.
Planning for Decentralized Control of Multiple Robots Under Uncertainty
We describe a probabilistic framework for synthesizing control policies for general multi-robot systems, given environment and sensor models and a cost function.
Incremental Clustering and Expansion for Faster Optimal Planning in Dec-POMDPs
We provide theoretical guarantees that, when a suitable heuristic is used, both incremental clustering and incremental expansion yield algorithms that are both complete and search equivalent.
Policy Iteration for Decentralized Control of Markov Decision Processes
The main contribution of this paper is an optimal policy iteration algorithm for solving DEC-POMDPs.
