Search Results for author:
Found 18 papers, 11 papers with code
Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning
Inspired by human conscious planning, we propose Skipper, a model-based reinforcement learning framework utilizing spatio-temporal abstractions to generalize better in novel situations.
Replay Buffer with Local Forgetting for Adapting to Local Environment Changes in Deep Model-Based Reinforcement Learning
This is challenging for deep-learning-based world models due to catastrophic forgetting.
Model-based Reinforcement Learning
reinforcement-learning
+1
Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information
We find that contemporary representation learning techniques can fail on datasets where the noise is a complex and time dependent process, which is prevalent in practical applications.
Modular Lifelong Reinforcement Learning via Neural Composition
Empirically, we demonstrate that neural composition indeed captures the underlying structure of this space of problems.
Towards Evaluating Adaptivity of Model-Based Reinforcement Learning Methods
We empirically validate these insights in the case of linear function approximation by demonstrating that a modified version of linear Dyna achieves effective adaptation to local changes.
Model-based Reinforcement Learning
reinforcement-learning
+1
One-Shot Learning from a Demonstration with Hierarchical Latent Language
Humans have the capability, aided by the expressive compositionality of their language, to learn quickly by demonstration.
Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks
We propose the k-Shortest-Path (k-SP) constraint: a novel constraint on the agent's trajectory that improves the sample efficiency in sparse-reward MDPs.
Systematic generalisation with group invariant predictions
We consider situations where the presence of dominant simpler correlations with the target variable in a training set can cause an SGD-trained neural network to be less reliant on more persistently-correlating complex features.
A Deeper Look at Discounting Mismatch in Actor-Critic Algorithms
In the second scenario, we consider optimizing a discounted objective ($\gamma < 1$) and propose to interpret the omission of the discounting in the actor update from an auxiliary task perspective and provide supporting empirical results.
The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learning
For example, the common single-task sample-efficiency metric conflates improvements due to model-based learning with various other aspects, such as representation learning, making it difficult to assess true progress on model-based RL.
Model-based Reinforcement Learning
Reinforcement Learning (RL)
+1
Using a Logarithmic Mapping to Enable Lower Discount Factors in Reinforcement Learning
In an effort to better understand the different ways in which the discount factor affects the optimization process in reinforcement learning, we designed a set of experiments to study each effect in isolation.
Learning Invariances for Policy Generalization
While recent progress has spawned very powerful machine learning systems, those agents remain extremely specialized and fail to transfer the knowledge they gain to similar yet unseen tasks.
Hybrid Reward Architecture for Reinforcement Learning
One of the main challenges in reinforcement learning (RL) is generalisation.
Multi-Advisor Reinforcement Learning
We consider tackling a single-agent RL problem by distributing it to $n$ learners.
Separation of Concerns in Reinforcement Learning
In this paper, we propose a framework for solving a single-agent task by using multiple agents, each focusing on different aspects of the task.
Effective Multi-step Temporal-Difference Learning for Non-Linear Function Approximation
Furthermore, based on our analysis, we propose a new multi-step TD method for non-linear function approximation that addresses this issue.
True Online Temporal-Difference Learning
Our results suggest that the true online methods indeed dominate the regular methods.
An Empirical Evaluation of True Online TD(λ)
Our results confirm the strength of true online TD({\lambda}): 1) for sparse feature vectors, the computational overhead with respect to TD({\lambda}) is minimal; for non-sparse features the computation time is at most twice that of TD({\lambda}), 2) across all domains/representations the learning speed of true online TD({\lambda}) is often better, but never worse than that of TD({\lambda}), and 3) true online TD({\lambda}) is easier to use, because it does not require choosing between trace types, and it is generally more stable with respect to the step-size.
