Search Results for author: Michael Littman

Found 19 papers, 1 papers with code

Does DQN really learn? Exploring adversarial training schemes in Pong

no code implementations20 Mar 2022 Bowen He, Sreehari Rammohan, Jessica Forde, Michael Littman

In this work, we study two self-play training schemes, Chainer and Pool, and show they lead to improved agent performance in Atari Pong compared to a standard DQN agent -- trained against the built-in Atari opponent.

Learning Generalizable Behavior via Visual Rewrite Rules

no code implementations9 Dec 2021 Yiheng Xie, Mingxuan Li, Shangqun Yu, Michael Littman

Though deep reinforcement learning agents have achieved unprecedented success in recent years, their learned policies can be brittle, failing to generalize to even slight modifications of their environments or unfamiliar situations.

Reinforcement Learning for General LTL Objectives Is Intractable

no code implementations24 Nov 2021 Cambridge Yang, Michael Littman, Michael Carbin

In recent years, researchers have made significant progress in devising reinforcement-learning algorithms for optimizing linear temporal logic (LTL) objectives and LTL-like objectives.

reinforcement-learning

Reinforcement Learning with General LTL Objectives is Intractable

no code implementations AAAI Workshop CLeaR 2022 Cambridge Yang, Michael Littman, Michael Carbin

In recent years, researchers have made significant progress in devising reinforcement-learning algorithms for optimizing linear temporal logic (LTL) objectives and LTL-like objectives.

reinforcement-learning

Learning Finite Linear Temporal Logic Specifications with a Specialized Neural Operator

no code implementations7 Nov 2021 Homer Walke, Daniel Ritter, Carl Trimbach, Michael Littman

Finite linear temporal logic ($\mathsf{LTL}_f$) is a powerful formal representation for modeling temporal sequences.

Coarse-Grained Smoothness for RL in Metric Spaces

no code implementations23 Oct 2021 Omer Gottesman, Kavosh Asadi, Cameron Allen, Sam Lobel, George Konidaris, Michael Littman

We propose a new coarse-grained smoothness definition that generalizes the notion of Lipschitz continuity, is more widely applicable, and allows us to compute significantly tighter bounds on Q-functions, leading to improved learning.

Decision Making

Bayesian Exploration for Lifelong Reinforcement Learning

no code implementations29 Sep 2021 Haotian Fu, Shangqun Yu, Michael Littman, George Konidaris

A central question in reinforcement learning (RL) is how to leverage prior knowledge to accelerate learning in new tasks.

reinforcement-learning

Task Scoping: Generating Task-Specific Abstractions for Planning

no code implementations17 Oct 2020 Nishanth Kumar, Michael Fishman, Natasha Danas, Michael Littman, Stefanie Tellex, George Konidaris

A generally intelligent agent requires an open-scope world model: one rich enough to tackle any of the wide range of tasks it may be asked to solve over its operational lifetime.

Teaching with IMPACT

no code implementations14 Mar 2019 Carl Trimbach, Michael Littman

Like many problems in AI in their general form, supervised learning is computationally intractable.

ReNeg and Backseat Driver: Learning from Demonstration with Continuous Human Feedback

no code implementations ICLR 2019 Jacob Beck, Zoe Papakipos, Michael Littman

Our framework learns continuous control from sub-optimal demonstration and evaluative feedback collected before training.

Continuous Control

Measuring and Characterizing Generalization in Deep Reinforcement Learning

no code implementations7 Dec 2018 Sam Witty, Jun Ki Lee, Emma Tosch, Akanksha Atrey, Michael Littman, David Jensen

We re-examine what is meant by generalization in RL, and propose several definitions based on an agent's performance in on-policy, off-policy, and unreachable states.

reinforcement-learning Representation Learning

Finding Options that Minimize Planning Time

no code implementations16 Oct 2018 Yuu Jinnai, David Abel, D. Ellis Hershkowitz, Michael Littman, George Konidaris

We formalize the problem of selecting the optimal set of options for planning as that of computing the smallest set of options so that planning converges in less than a given maximum of value-iteration passes.

Personalized Education at Scale

no code implementations24 Sep 2018 Sam Saarinen, Evan Cater, Michael Littman

Tailoring the presentation of information to the needs of individual students leads to massive gains in student outcomes~\cite{bloom19842}.

reinforcement-learning

Policy and Value Transfer in Lifelong Reinforcement Learning

no code implementations ICML 2018 David Abel, Yuu Jinnai, Sophie Yue Guo, George Konidaris, Michael Littman

We consider the problem of how best to use prior experience to bootstrap lifelong learning, where an agent faces a series of task instances drawn from some task distribution.

reinforcement-learning

State Abstractions for Lifelong Reinforcement Learning

no code implementations ICML 2018 David Abel, Dilip Arumugam, Lucas Lehnert, Michael Littman

We introduce two new classes of abstractions: (1) transitive state abstractions, whose optimal form can be computed efficiently, and (2) PAC state abstractions, which are guaranteed to hold with respect to a distribution of tasks.

reinforcement-learning

Mean Actor Critic

2 code implementations1 Sep 2017 Cameron Allen, Kavosh Asadi, Melrose Roderick, Abdel-rahman Mohamed, George Konidaris, Michael Littman

We propose a new algorithm, Mean Actor-Critic (MAC), for discrete-action continuous-state reinforcement learning.

Atari Games reinforcement-learning

Cannot find the paper you are looking for? You can Submit a new open access paper.