Alert button
Picture for Sam Devlin

Sam Devlin

Alert button

Visual Encoders for Data-Efficient Imitation Learning in Modern Video Games

Dec 04, 2023
Lukas Schäfer, Logan Jones, Anssi Kanervisto, Yuhan Cao, Tabish Rashid, Raluca Georgescu, Dave Bignell, Siddhartha Sen, Andrea Treviño Gavito, Sam Devlin

Viaarxiv icon

Adaptive Scaffolding in Block-Based Programming via Synthesizing New Tasks as Pop Quizzes

Mar 28, 2023
Ahana Ghosh, Sebastian Tschiatschek, Sam Devlin, Adish Singla

Viaarxiv icon

Navigates Like Me: Understanding How People Evaluate Human-Like AI in Video Games

Mar 02, 2023
Stephanie Milani, Arthur Juliani, Ida Momennejad, Raluca Georgescu, Jaroslaw Rzpecki, Alison Shaw, Gavin Costello, Fei Fang, Sam Devlin, Katja Hofmann

Figure 1 for Navigates Like Me: Understanding How People Evaluate Human-Like AI in Video Games
Figure 2 for Navigates Like Me: Understanding How People Evaluate Human-Like AI in Video Games
Figure 3 for Navigates Like Me: Understanding How People Evaluate Human-Like AI in Video Games
Figure 4 for Navigates Like Me: Understanding How People Evaluate Human-Like AI in Video Games
Viaarxiv icon

Trust-Region-Free Policy Optimization for Stochastic Policies

Feb 15, 2023
Mingfei Sun, Benjamin Ellis, Anuj Mahajan, Sam Devlin, Katja Hofmann, Shimon Whiteson

Figure 1 for Trust-Region-Free Policy Optimization for Stochastic Policies
Figure 2 for Trust-Region-Free Policy Optimization for Stochastic Policies
Viaarxiv icon

Contrastive Meta-Learning for Partially Observable Few-Shot Learning

Jan 30, 2023
Adam Jelley, Amos Storkey, Antreas Antoniou, Sam Devlin

Figure 1 for Contrastive Meta-Learning for Partially Observable Few-Shot Learning
Figure 2 for Contrastive Meta-Learning for Partially Observable Few-Shot Learning
Figure 3 for Contrastive Meta-Learning for Partially Observable Few-Shot Learning
Figure 4 for Contrastive Meta-Learning for Partially Observable Few-Shot Learning
Viaarxiv icon

Imitating Human Behaviour with Diffusion Models

Jan 25, 2023
Tim Pearce, Tabish Rashid, Anssi Kanervisto, Dave Bignell, Mingfei Sun, Raluca Georgescu, Sergio Valcarcel Macua, Shan Zheng Tan, Ida Momennejad, Katja Hofmann, Sam Devlin

Figure 1 for Imitating Human Behaviour with Diffusion Models
Figure 2 for Imitating Human Behaviour with Diffusion Models
Figure 3 for Imitating Human Behaviour with Diffusion Models
Figure 4 for Imitating Human Behaviour with Diffusion Models
Viaarxiv icon

UniMASK: Unified Inference in Sequential Decision Problems

Nov 20, 2022
Micah Carroll, Orr Paradise, Jessy Lin, Raluca Georgescu, Mingfei Sun, David Bignell, Stephanie Milani, Katja Hofmann, Matthew Hausknecht, Anca Dragan, Sam Devlin

Figure 1 for UniMASK: Unified Inference in Sequential Decision Problems
Figure 2 for UniMASK: Unified Inference in Sequential Decision Problems
Figure 3 for UniMASK: Unified Inference in Sequential Decision Problems
Figure 4 for UniMASK: Unified Inference in Sequential Decision Problems
Viaarxiv icon

Towards Flexible Inference in Sequential Decision Problems via Bidirectional Transformers

Apr 28, 2022
Micah Carroll, Jessy Lin, Orr Paradise, Raluca Georgescu, Mingfei Sun, David Bignell, Stephanie Milani, Katja Hofmann, Matthew Hausknecht, Anca Dragan, Sam Devlin

Figure 1 for Towards Flexible Inference in Sequential Decision Problems via Bidirectional Transformers
Figure 2 for Towards Flexible Inference in Sequential Decision Problems via Bidirectional Transformers
Figure 3 for Towards Flexible Inference in Sequential Decision Problems via Bidirectional Transformers
Figure 4 for Towards Flexible Inference in Sequential Decision Problems via Bidirectional Transformers
Viaarxiv icon

Monotonic Improvement Guarantees under Non-stationarity for Decentralized PPO

Jan 31, 2022
Mingfei Sun, Sam Devlin, Katja Hofmann, Shimon Whiteson

Figure 1 for Monotonic Improvement Guarantees under Non-stationarity for Decentralized PPO
Figure 2 for Monotonic Improvement Guarantees under Non-stationarity for Decentralized PPO
Figure 3 for Monotonic Improvement Guarantees under Non-stationarity for Decentralized PPO
Figure 4 for Monotonic Improvement Guarantees under Non-stationarity for Decentralized PPO
Viaarxiv icon

You May Not Need Ratio Clipping in PPO

Jan 31, 2022
Mingfei Sun, Vitaly Kurin, Guoqing Liu, Sam Devlin, Tao Qin, Katja Hofmann, Shimon Whiteson

Figure 1 for You May Not Need Ratio Clipping in PPO
Figure 2 for You May Not Need Ratio Clipping in PPO
Figure 3 for You May Not Need Ratio Clipping in PPO
Figure 4 for You May Not Need Ratio Clipping in PPO
Viaarxiv icon