Search Results for author:
Found 40 papers, 16 papers with code
Plasticity as the Mirror of Empowerment
In this paper, we ground this concept in a universal agent-centric measure that we refer to as plasticity, and reveal a fundamental connection to empowerment.
AuPair: Golden Example Pairs for Code Repair
Our algorithm yields a significant boost in performance compared to best-of-$N$ and self-repair, and also exhibits strong generalisation across datasets and models.
Agency Is Frame-Dependent
Agency is a system's capacity to steer outcomes toward a goal, and is a central topic of study across biology, philosophy, cognitive science, and artificial intelligence.
Boundless Socratic Learning with Language Games
An agent trained within a closed system can master any desired capability, as long as the following three conditions hold: (a) it receives sufficiently informative and aligned feedback, (b) its coverage of experience/data is broad enough, and (c) it has sufficient capacity and resource.
Open-Endedness is Essential for Artificial Superhuman Intelligence
In this position paper, we argue that the ingredients are now in place to achieve openendedness in AI systems with respect to a human observer.
Vision-Language Models as a Source of Rewards
Building generalist agents that can accomplish many goals in rich open-ended environments is one of the research frontiers for reinforcement learning.
Discovering Attention-Based Genetic Algorithms via Meta-Black-Box Optimization
Genetic algorithms constitute a family of black-box optimization algorithms, which take inspiration from the principles of biological evolution.
Scaling Goal-based Exploration via Pruning Proto-goals
One of the gnarliest challenges in reinforcement learning (RL) is exploration that scales to vast domains, where novelty-, or coverage-seeking behaviour falls short.
Discovering Evolution Strategies via Meta-Black-Box Optimization
Optimizing functions without access to gradients is the remit of black-box methods such as evolution strategies.
The Phenomenon of Policy Churn
We identify and study the phenomenon of policy churn, that is, the rapid change of the greedy policy in value-based reinforcement learning.
Model-Value Inconsistency as a Signal for Epistemic Uncertainty
Unlike prior work which estimates uncertainty by training an ensemble of many models and/or value functions, this approach requires only the single model and value function which are already being learned in most model-based reinforcement learning algorithms.
Model-based Reinforcement Learning
Rolling Shutter Correction
When should agents explore?
Exploration remains a central challenge for reinforcement learning (RL).
Return-based Scaling: Yet Another Normalisation Trick for Deep RL
Scaling issues are mundane yet irritating for practitioners of reinforcement learning.
Policy Evaluation Networks
The core idea of this paper is to flip this convention and estimate the value of many policies, for a single set of states.
Adapting Behaviour for Learning Progress
Determining what experience to generate to best facilitate learning (i. e. exploration) is one of the distinguishing features and open challenges in reinforcement learning.
Conditional Importance Sampling for Off-Policy Learning
We theoretically analyse this space, and concretely investigate several algorithms that arise from this framework.
Non-Differentiable Supervised Learning with Evolution Strategies and Hybrid Methods
While using ES for differentiable parameters is computationally impractical (although possible), we show that a hybrid approach is practically feasible in the case where the model has both differentiable and non-differentiable parameters.
Ray Interference: a Source of Plateaus in Deep Reinforcement Learning
Rather than proposing a new method, this paper investigates an issue present in existing learning algorithms.
Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement
In this paper we extend the SFs & GPI framework in two ways.
Universal Successor Features Approximators
We focus on one aspect in particular, namely the ability to generalise to unseen tasks.
The Barbados 2018 List of Open Issues in Continual Learning
We want to make progress toward artificial general intelligence, namely general-purpose agents that autonomously learn how to competently act in complex environments.
Meta-Learning by the Baldwin Effect
The scope of the Baldwin effect was recently called into question by two papers that closely examined the seminal work of Hinton and Nowlan.
Unicorn: Continual Learning with a Universal, Off-policy Agent
Some real-world domains are best characterized as a single task, but for others this perspective is limiting.
Natural Value Approximators: Learning when to Trust Past Estimates
Neural networks have a smooth initial inductive bias, such that small changes in input do not lead to large changes in output.
Rainbow: Combining Improvements in Deep Reinforcement Learning
The deep reinforcement learning community has made several independent improvements to the DQN algorithm.
StarCraft II: A New Challenge for Reinforcement Learning
Finally, we present initial baseline results for canonical deep reinforcement learning agents applied to the StarCraft II domain.
Ranked #1 on
Starcraft II
on MoveToBeacon
Deep Q-learning from Demonstrations
We present an algorithm, Deep Q-learning from Demonstrations (DQfD), that leverages small sets of demonstration data to massively accelerate the learning process even from relatively small amounts of demonstration data and is able to automatically assess the necessary ratio of demonstration data while learning thanks to a prioritized replay mechanism.
FeUdal Networks for Hierarchical Reinforcement Learning
We introduce FeUdal Networks (FuNs): a novel architecture for hierarchical reinforcement learning.
Hierarchical Reinforcement Learning
reinforcement-learning
+2
The Predictron: End-To-End Learning and Planning
One of the key challenges of artificial intelligence is to learn models that are effective in the context of planning.
Reinforcement Learning with Unsupervised Auxiliary Tasks
We also introduce a novel mechanism for focusing this representation upon extrinsic rewards, so that learning can rapidly adapt to the most relevant aspects of the actual task.
Successor Features for Transfer in Reinforcement Learning
Transfer in reinforcement learning refers to the notion that generalization should occur not only within a task but also across tasks.
Learning to learn by gradient descent by gradient descent
The move from hand-designed features to learned features in machine learning has been wildly successful.
Unifying Count-Based Exploration and Intrinsic Motivation
We consider an agent's uncertainty about its environment and the problem of generalizing this uncertainty across observations.
Ranked #10 on
Atari Games
on Atari 2600 Montezuma's Revenge
Dueling Network Architectures for Deep Reinforcement Learning
In recent years there have been many successes of using deep representations in reinforcement learning.
Ranked #1 on
Atari Games
on Atari 2600 Pong
Prioritized Experience Replay
Experience replay lets online reinforcement learning agents remember and reuse experiences from the past.
Ranked #3 on
Atari Games
on Atari 2600 Kangaroo
Unit Tests for Stochastic Optimization
Optimization by stochastic gradient descent is an important component of many large-scale machine learning algorithms.
Adaptive learning rates and parallelization for stochastic, sparse, non-smooth gradients
Recent work has established an empirically successful framework for adapting learning rates for stochastic gradient descent (SGD).
No More Pesky Learning Rates
The performance of stochastic gradient descent (SGD) depends critically on how learning rates are tuned and decreased over time.
Measuring Intelligence through Games
Artificial general intelligence (AGI) refers to research aimed at tackling the full problem of artificial intelligence, that is, create truly intelligent agents.
Natural Evolution Strategies
This paper presents Natural Evolution Strategies (NES), a recent family of algorithms that constitute a more principled approach to black-box optimization than established evolutionary algorithms.
