← Core AI
Artificial Intelligence › Core AI ›

Agent Systems

3885 directly classified papers

Papers per year

Papers

ProTo: Program-Guided Transformer for Program-Guided Tasks NIPS 2021
Sparsely Changing Latent States for Prediction and Planning in Partially Observable Domains NIPS 2021
The Sensory Neuron as a Transformer: Permutation-Invariant Neural Networks for Reinforcement Learning NIPS 2021
Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability NIPS 2021
Robust Inverse Reinforcement Learning under Transition Dynamics Mismatch NIPS 2021
Towards mental time travel: a hierarchical memory for reinforcement learning agents NIPS 2021
Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learning NIPS 2021
Program Synthesis Guided Reinforcement Learning for Partially Observed Environments NIPS 2021
Shaping embodied agent behavior with activity-context priors from egocentric video NIPS 2021
Discovery of Options via Meta-Learned Subgoals NIPS 2021
Fully Gap-Dependent Bounds for Multinomial Logit Bandit AISTATS 2021
An Efficient Algorithm For Generalized Linear Bandit: Online Stochastic Gradient Descent and Thompson Sampling AISTATS 2021
Robots that Help Humans Build Better Mental Models of Robots AAAI 2021
Bot-Adversarial Dialogue for Safe Conversational Agents NAACL 2021
Strategic Classification in the Dark ICML 2021
Navigation Turing Test (NTT): Learning to Evaluate Human-Like Navigation ICML 2021
On Reinforcement Learning with Adversarial Corruption and Its Application to Block MDP ICML 2021
Learning and Planning in Average-Reward Markov Decision Processes ICML 2021
Hierarchical Object-to-Zone Graph for Object Navigation ICCV 2021
Task-Optimal Exploration in Linear Dynamical Systems ICML 2021
Neuro-algorithmic Policies Enable Fast Combinatorial Generalization ICML 2021
Interactive Learning from Activity Description ICML 2021
Provably Efficient Learning of Transferable Rewards ICML 2021
Counterfactual Credit Assignment in Model-Free Reinforcement Learning ICML 2021
GridToPix: Training Embodied Agents With Minimal Supervision ICCV 2021