Tag: Reinforcement Learning

AI Machine Learning & Data Science Research

DeepMind’s Fictitious Co-Play Trains RL Agents to Collaborate with Novel Humans Without Using Human Data

A DeepMind research team explores the problem of how to train agents to collaborate well with novel human partners without using human data and presents Fictitious Co-Play (FCP), a surprisingly simple approach designed to address this challenge.

AI Machine Learning & Data Science Research

DeepMind & IDSIA Introduce Symmetries to Black-Box MetaRL to Improve Its Generalization Ability

In the paper Introducing Symmetries to Black Box Meta Reinforcement Learning, a research team from DeepMind and The Swiss AI Lab IDSIA explores the role of symmetries in meta generalization and shows that introducing more symmetries to black-box meta-learners can improve their ability to generalize to unseen action and observation spaces, tasks, and environments.

AI Machine Learning & Data Science Research

CMU, Google & UC Berkeley Propose Robust Predictable Control Policies for RL Agents

A research team from Carnegie Mellon University, Google Brain and UC Berkeley proposes a robust predictable control (RPC) method for learning reinforcement learning policies that use fewer bits of information. This simple and theoretically-justified algorithm achieves much tighter compression, is more robust, and generalizes better than prior methods, achieving up to 5× higher rewards than a standard information bottleneck.

AI Machine Learning & Data Science Research

Pieter Abbeel Team’s Decision Transformer Abstracts RL as Sequence Modelling

A research team from UC Berkeley, Facebook AI Research and Google Brain abstracts Reinforcement Learning (RL) as a sequence modelling problem. Their proposed Decision Transformer simply outputs optimal actions by leveraging a causally masked transformer, yet matches or exceeds state-of-the-art model-free offline RL baselines on Atari, OpenAI Gym, and Key-to-Door tasks.

AI Machine Learning & Data Science Research

What Matters in Adversarial Imitation Learning? Google Brain Study Reveals Valuable Insights

A research team from Google Brain conducts a comprehensive empirical study on more than fifty choices in a generic adversarial imitation learning framework and explores their impacts on large-scale (>500k trained agents) continuous-control tasks to provide practical insights and recommendations for designing novel and effective AIL algorithms.

AI Machine Learning & Data Science Research

Yoshua Bengio Team’s Recurrent Independent Mechanisms Endow RL Agents With Out-of-Distribution Adaptation and Generalization Abilities

A research team from the University of Montreal and Max Planck Institute for Intelligent Systems constructs a reinforcement learning agent whose knowledge and reward function can be reused across tasks, along with an attention mechanism that dynamically selects unchangeable knowledge pieces to enable out-of-distribution adaptation and generalization.