Alert button
Picture for Ufuk Topcu

Ufuk Topcu

Alert button

Temporal-Logic-Based Reward Shaping for Continuing Learning Tasks

Jul 03, 2020
Yuqian Jiang, Sudarshanan Bharadwaj, Bo Wu, Rishi Shah, Ufuk Topcu, Peter Stone

Figure 1 for Temporal-Logic-Based Reward Shaping for Continuing Learning Tasks
Figure 2 for Temporal-Logic-Based Reward Shaping for Continuing Learning Tasks
Figure 3 for Temporal-Logic-Based Reward Shaping for Continuing Learning Tasks
Figure 4 for Temporal-Logic-Based Reward Shaping for Continuing Learning Tasks
Viaarxiv icon

Active Finite Reward Automaton Inference and Reinforcement Learning Using Queries and Counterexamples

Jun 28, 2020
Zhe Xu, Bo Wu, Daniel Neider, Ufuk Topcu

Figure 1 for Active Finite Reward Automaton Inference and Reinforcement Learning Using Queries and Counterexamples
Figure 2 for Active Finite Reward Automaton Inference and Reinforcement Learning Using Queries and Counterexamples
Figure 3 for Active Finite Reward Automaton Inference and Reinforcement Learning Using Queries and Counterexamples
Figure 4 for Active Finite Reward Automaton Inference and Reinforcement Learning Using Queries and Counterexamples
Viaarxiv icon

Scalable Synthesis of Minimum-Information Linear-Gaussian Control by Distributed Optimization

Apr 11, 2020
Murat Cubuktepe, Takashi Tanaka, Ufuk Topcu

Figure 1 for Scalable Synthesis of Minimum-Information Linear-Gaussian Control by Distributed Optimization
Figure 2 for Scalable Synthesis of Minimum-Information Linear-Gaussian Control by Distributed Optimization
Figure 3 for Scalable Synthesis of Minimum-Information Linear-Gaussian Control by Distributed Optimization
Figure 4 for Scalable Synthesis of Minimum-Information Linear-Gaussian Control by Distributed Optimization
Viaarxiv icon

Verifiable RNN-Based Policies for POMDPs Under Temporal Logic Constraints

Feb 13, 2020
Steven Carr, Nils Jansen, Ufuk Topcu

Figure 1 for Verifiable RNN-Based Policies for POMDPs Under Temporal Logic Constraints
Figure 2 for Verifiable RNN-Based Policies for POMDPs Under Temporal Logic Constraints
Figure 3 for Verifiable RNN-Based Policies for POMDPs Under Temporal Logic Constraints
Figure 4 for Verifiable RNN-Based Policies for POMDPs Under Temporal Logic Constraints
Viaarxiv icon

Adaptive Teaching of Temporal Logic Formulas to Learners with Preferences

Jan 27, 2020
Zhe Xu, Yuxin Chen, Ufuk Topcu

Figure 1 for Adaptive Teaching of Temporal Logic Formulas to Learners with Preferences
Figure 2 for Adaptive Teaching of Temporal Logic Formulas to Learners with Preferences
Figure 3 for Adaptive Teaching of Temporal Logic Formulas to Learners with Preferences
Figure 4 for Adaptive Teaching of Temporal Logic Formulas to Learners with Preferences
Viaarxiv icon

Active Task-Inference-Guided Deep Inverse Reinforcement Learning

Jan 24, 2020
Farzan Memarian, Zhe Xu, Bo Wu, Min Wen, Ufuk Topcu

Figure 1 for Active Task-Inference-Guided Deep Inverse Reinforcement Learning
Figure 2 for Active Task-Inference-Guided Deep Inverse Reinforcement Learning
Figure 3 for Active Task-Inference-Guided Deep Inverse Reinforcement Learning
Figure 4 for Active Task-Inference-Guided Deep Inverse Reinforcement Learning
Viaarxiv icon

Learning and Planning for Time-Varying MDPs Using Maximum Likelihood Estimation

Nov 29, 2019
Melkior Ornik, Ufuk Topcu

Figure 1 for Learning and Planning for Time-Varying MDPs Using Maximum Likelihood Estimation
Figure 2 for Learning and Planning for Time-Varying MDPs Using Maximum Likelihood Estimation
Figure 3 for Learning and Planning for Time-Varying MDPs Using Maximum Likelihood Estimation
Figure 4 for Learning and Planning for Time-Varying MDPs Using Maximum Likelihood Estimation
Viaarxiv icon

Strategy Synthesis for Surveillance-Evasion Games with Learning-Enabled Visibility Optimization

Nov 18, 2019
Suda Bharadwaj, Louis Ly, Bo Wu, Richard Tsai, Ufuk Topcu

Figure 1 for Strategy Synthesis for Surveillance-Evasion Games with Learning-Enabled Visibility Optimization
Figure 2 for Strategy Synthesis for Surveillance-Evasion Games with Learning-Enabled Visibility Optimization
Figure 3 for Strategy Synthesis for Surveillance-Evasion Games with Learning-Enabled Visibility Optimization
Figure 4 for Strategy Synthesis for Surveillance-Evasion Games with Learning-Enabled Visibility Optimization
Viaarxiv icon

Decentralized Runtime Synthesis of Shields for Multi-Agent Systems

Oct 23, 2019
Dhananjay Raju, Suda Bharadwaj, Ufuk Topcu

Figure 1 for Decentralized Runtime Synthesis of Shields for Multi-Agent Systems
Figure 2 for Decentralized Runtime Synthesis of Shields for Multi-Agent Systems
Figure 3 for Decentralized Runtime Synthesis of Shields for Multi-Agent Systems
Figure 4 for Decentralized Runtime Synthesis of Shields for Multi-Agent Systems
Viaarxiv icon

Online Active Perception for Partially Observable Markov Decision Processes with Limited Budget

Oct 04, 2019
Mahsa Ghasemi, Ufuk Topcu

Figure 1 for Online Active Perception for Partially Observable Markov Decision Processes with Limited Budget
Figure 2 for Online Active Perception for Partially Observable Markov Decision Processes with Limited Budget
Figure 3 for Online Active Perception for Partially Observable Markov Decision Processes with Limited Budget
Viaarxiv icon