Workshop on Human-aligned Reinforcement Learning for Autonomous Agents and Robots

Full session video here

Video and length (mm:ss)	Speaker	Topic
Video here 08:48	Welcome and introduction
Video 1 here 12:07 Video 2 here 09:06	Contribution talks - Session 1 Should I Trust You? Incorporating Unreliable Expert Advice in Human-Agent Interaction Tamlin Love, Ritesh Ajoodha and Benjamin Rosman Mixing Human Demonstrations with Self-Exploration in Experience Replay for Deep Reinforcement Learning Akansel Cosgun and Dylan Klein


Video here 31:50	Peter Vamplew	Multiobjective Approaches to Human-Aligned Reinforcement Learning
Video here 31:33	Cornelius Weber	Hybrid Neural Learning for Interactive Robots
Video here 30:22	Benjamin Rosman	Modelling Imprecise Human Collaborators
Video here 28:17	Jens Kober	Reinforcement Learning with Interactive Corrections
Video 1 here 08:50 Video 2 here 07:17	Contribution talks - Session 2 Explanations In, Explanations Out: Human-in-the-Loop Social Navigation Learning Jakob Karalus, Amar Halilovic and Felix Lindner Learning Proxemic Behavior Using Reinforcement Learning with Cognitive Agents Cristian Camilo Millán Arias, Bruno Fernandes and Francisco Cruz


Video here 37:17	Richard Dazeley	Broad-XAI: Human-aligned conversational explanations
Video here 28:39	Alessandra Sciutti	More Humane Learning
Video here 20:55	Bruno Fernandes	Reinforcement Learning for Robot Control and Interaction
Video here 32:55	Matthew Taylor	Agents learning from humans -- what the heck do you want me to do?
Video 1 here 11:36 Video 2 here 07:28	Contribution talks - Session 3 Policy Regularization for Legible Behavior Michele Persiani Explainable Deep Reinforcement Learning Using Introspection in a Non-episodic Task Angel Ayala, Francisco Cruz, Bruno Fernandes and Richard Dazeley


Video here 25:01	George Konidaris	Grounded Symbolic Representations for Human-Robot Communication
Video here 31:44	W. Bradley Knox	Reward (Mis)design for Autonomous Driving
Video here 25:47	Patrick Pilarski	Constructivism in Tightly Coupled Human Machine Interfaces
Video here 30:57	Felipe Leno Da Silva	Action Advising for Accelerating Multiagent Reinforcement Learning
Video here 03:41	Farewell and conclusions