Study OOD generalization in meta-reinforcement learning using information theory.
problem Understanding how meta-reinforcement learning handles distribution shifts.
method Information-theoretic analysis of Markov Decision Processes and gradient-based algorithms.
result Established fine-grained generalization bounds for meta-reinforcement learning.
Study on meta-reinforcement learning generalization in high-dimensional tasks.
problem Generalization performance of meta-reinforcement learning algorithms in high-dimensional tasks.
method High-dimensional, procedurally generated environments.
result Meta-reinforcement learning algorithms exhibit strong overfitting on challenging tasks.
Novel Bayesian meta-reinforcement learning framework improves traffic signal control robustness.
problem Lack of robustness and stability in adaptation for traffic signal control.
method Value-based Bayesian meta-reinforcement learning framework BM-DQN with fast-adaptation variation and DQN fast-update advantage.
result Framework adapts more quickly and robustly to new scenarios than previous methods.
Bayesian meta-reinforcement learning improves over point estimates with Laplace approximation.
problem Improving meta-reinforcement learning by providing full posterior distributions.
method Augmenting point estimates with Laplace approximation for full posterior distributions.
result Our method performs similarly to variational baselines with fewer parameters.
Meta-reinforcement learning algorithms can enable robots to acquire new skills much more quickly, by leveraging prior experience to learn how to learn. However, much of the current research on meta-reinforcement learning focuses on task distributions that are very narrow. For example, a commonly used meta-reinforcement…
Algorithm learns new tasks efficiently from past experience.
problem Lack of robustness to distributional shift in meta-reinforcement learning.
method Model Identification and Experience Relabeling (MIER) using dynamics models.
result Efficient extrapolation to out-of-distribution tasks.
Meta-reinforcement learning improves fault-adaptive control efficiency.
problem Adaptive control under abrupt system faults with strict time constraints.
method Model-agnostic meta learning (MAML) with a fault library of prior policies.
result Improved sample efficiency and quick adaptation to new faults.
New symmetries improve meta-reinforcement learning's generalization.
problem Black-box meta reinforcement learning struggles with generalization.
method Introduce symmetries to a black-box meta RL system.
result Incorporating symmetries improves generalization to new environments.
New method improves meta-reinforcement learning efficiency.
problem Sample inefficiency in meta-reinforcement learning.
method Hindsight Foresight Relabeling (HFR) method.
result HFR improves performance on various meta-reinforcement learning tasks.
AdMRL improves meta-reinforcement learning by minimizing worst-case sub-optimality gap.
problem Meta-reinforcement learning's sensitivity to task distribution shift.
method Model-based adversarial approach with minimax objective and alternating optimization.
result Efficacy in worst-case performance, generalization to out-of-distribution tasks, and sample efficiency.
Study improves self-driving safety in dynamic environments.
problem Safe self-driving in non-stationary urban settings.
method Neurosymbolic Meta-Reinforcement Lookahead Learning (NUMERLA).
result Self-driving agents can adapt safely in real-time.
Meta-learning algorithms use past experience to learn to quickly solve new tasks. In the context of reinforcement learning, meta-learning algorithms acquire reinforcement learning procedures to solve new problems more efficiently by utilizing experience from prior tasks. The performance of meta-learning algorithms depe…
This work extends HiP-MDPs to robust state abstractions for multi-task and meta-reinforcement learning.
problem Limited observability of state in HiP-MDPs for real-world scenarios with rich observation spaces.
method Inspired by Block MDPs, the work extends HiP-MDPs to enable robust state abstractions for multi-task and meta-reinforcement learning.
result Transfer and generalization bounds based on task and state similarity, and sample complexity bounds that depend on the aggregate number of samples across tasks.
FOCAL tackles offline meta-reinforcement learning with efficient task inference and behavior regularization.
problem Efficiently adapt RL algorithms to unseen tasks without interactions, addressing bootstrapping errors and robust task inference.
method FOCAL combines behavior regularization, a deterministic context encoder, and a negative-power distance metric for efficient task inference.
result FOCAL outperforms prior algorithms on meta-RL benchmarks, demonstrating computational efficiency.
We present a new deep meta reinforcement learner, which we call Deep Episodic Value Iteration (DEVI). DEVI uses a deep neural network to learn a similarity metric for a non-parametric model-based reinforcement learning algorithm. Our model is trained end-to-end via back-propagation. Despite being trained using the mode…
Proves efficient learning of hierarchical structure in meta-reinforcement learning.
problem Lack of provable guarantees for learning hierarchical structures in reinforcement learning.
method Analyzed HRL in meta-RL setting with tabular transition dynamics, providing diversity conditions and regret bounds.
result Sample-efficient recovery of natural hierarchical structure with provable guarantees.
Biological evolution has distilled the experiences of many learners into the general learning algorithms of humans. Our novel meta reinforcement learning algorithm MetaGenRL is inspired by this process. MetaGenRL distills the experiences of many complex agents to meta-learn a low-complexity neural objective function th…
CausalCOMRL improves RL task representations by integrating causal relationships, enhancing generalizability.
problem Spurious correlations in context-based offline meta-reinforcement learning.
method CausalCOMRL integrates causal representation learning to uncover and incorporate causal relationships among task components.
result CausalCOMRL achieves better performance on meta-reinforcement learning benchmarks.
Paper tackles offline meta-reinforcement learning with a new algorithm.
problem Performing reinforcement learning on limited data from a new task.
method Meta-Actor Critic with Advantage Weighting (MACAW) algorithm.
result Achieves notable gains over prior methods on offline meta-RL benchmarks.
We consider Model-Agnostic Meta-Learning (MAML) methods for Reinforcement Learning (RL) problems, where the goal is to find a policy using data from several tasks represented by Markov Decision Processes (MDPs) that can be updated by one step of stochastic policy gradient for the realized MDP. In particular, using stoc…
CCM improves context for Meta-RL by contrastive learning.
problem Improving context for Meta-RL to enable task generalization.
method CCM framework using contrastive learning for context encoding and information-gain-based trajectory collection.
result CCM outperforms state-of-the-art algorithms in benchmarks and sparse-reward environments.
New meta-RL method avoids exploration-exploitation trade-off.
problem Learning to explore and exploit simultaneously in meta-RL.
method Developed new objectives for exploration and exploitation.
result DREAM outperforms existing methods on complex tasks.
In spite of the success of existing meta reinforcement learning methods, they still have difficulty in learning a meta policy effectively for RL problems with sparse reward. In this respect, we develop a novel meta reinforcement learning framework called Hyper-Meta RL(HMRL), for sparse reward RL problems. It is consist…
FLAP adapts policies quickly to new tasks using shared linear representations.
problem Adapting policies to new tasks efficiently and effectively.
method FLAP uses a shared linear representation and a separate adapter network for quick adaptation.
result FLAP achieves up to 8X faster adaptation and significantly better performance on out-of-distribution tasks.
Discovering and exploiting the causal structure in the environment is a crucial challenge for intelligent agents. Here we explore whether causal reasoning can emerge via meta-reinforcement learning. We train a recurrent network with model-free reinforcement learning to solve a range of problems that each contain causal…
A new approach combines prior knowledge with learning to adapt quickly to new tasks.
problem Adapting quickly to new tasks using prior knowledge.
method Combines behavior prior, robust off-policy learning, and value function representation.
result Achieves competitive adaptation performance compared to meta reinforcement learning baselines.
Deep reinforcement learning algorithms require large amounts of experience to learn an individual task. While in principle meta-reinforcement learning (meta-RL) algorithms enable agents to learn new skills from small amounts of experience, several major challenges preclude their practicality. Current methods rely heavi…
ContraBAR uses contrastive learning to learn Bayes-optimal policies in RL.
problem Learning optimal policies for unknown tasks sampled from a known distribution.
method Proposes ContraBAR, a meta RL algorithm using contrastive predictive coding (CPC) for belief inference.
result ContraBAR achieves comparable performance to state-of-the-art methods and is computationally efficient.
Empirical study shows consistent meta-RL algorithms adapt to OOD tasks.
problem Theoretical consistency of meta-RL algorithms and its practical implications.
method Empirical investigation of representative meta-RL algorithms, focusing on consistency and adaptation to out-of-distribution tasks.
result Theoretical consistent algorithms can adapt to OOD tasks, while inconsistent ones cannot, but can still fail for poor exploration.
New meta-reinforcement learning method improves performance in finite-horizon MDPs.
problem Improving meta-reinforcement learning in finite-horizon MDPs with shared optimal action-value functions.
method Proposes MTSRL and MTSRL+ algorithms with learned priors and covariance, coupled with prior-alignment technique for meta-regret guarantees.
result Achieves meta-regret guarantees with learned priors and covariance, outperforming prior-independent RL and bandit-only meta-baselines.
Novel meta-RL strategy improves efficiency in learning novel tasks.
problem Efficiency in learning novel tasks using deep RL.
method Decomposes meta-RL into task-exploration, task-inference, and task-fulfillment; uses deep networks and a task encoder.
result Improves sample efficiency and mitigates meta-overfitting.
Gradient-based meta-learners such as Model-Agnostic Meta-Learning (MAML) have shown strong few-shot performance in supervised and reinforcement learning settings. However, specifically in the case of meta-reinforcement learning (meta-RL), we can show that gradient-based meta-learners are sensitive to task distributions…
Meta-agent learns effective exploration from offline data.
problem Design a meta-agent to quickly maximize reward in unseen tasks.
method Bayesian RL approach with adaptive neural belief estimate.
result Meta-agent learns effective exploration behavior from diverse tasks.
Meta-learning improves drone trajectory design for dynamic wireless networks.
problem Designing optimal trajectories for energy-constrained drones in dynamic network environments.
method Proposes a meta-learning algorithm to adaptively tune a reinforcement learning solution for trajectory design.
result Meta-tuned RL yields faster convergence and improved communication performance compared to baseline algorithms.
GeneraLight improves traffic signal control models' generalization ability.
problem Overfitting and lack of generalization ability in RL TSC models.
method GeneraLight uses a meta-RL framework with a traffic flow generator based on GANs.
result GeneraLight significantly boosts generalization performance across different traffic flows.
PDTS improves robustness in sequential decision-making.
problem Robust active task sampling for efficient and reliable decision-making.
method Characterizes robust active task sampling as a Markov decision process, proposes PDTS method.
result Significantly improves zero-shot and few-shot adaptation robustness.
The stringent requirements of mobile edge computing (MEC) applications and functions fathom the high capacity and dense deployment of MEC hosts to the upcoming wireless networks. However, operating such high capacity MEC hosts can significantly increase energy consumption. Thus, a base station (BS) unit can act as a se…
DIVA generates diverse tasks for complex simulators, enabling adaptive agent training.
problem Lack of diverse training data for complex, open-ended simulators.
method Evolutionary approach using domain randomization and procedural generation.
result Successfully trains adaptive agent behavior in complex simulators.
Gradient-based methods for optimisation of objectives in stochastic settings with unknown or intractable dynamics require estimators of derivatives. We derive an objective that, under automatic differentiation, produces low-variance unbiased estimators of derivatives at any order. Our objective is compatible with arbit…
Most meta reinforcement learning (meta-RL) methods learn to adapt to new tasks by directly optimizing the parameters of policies over primitive action space. Such algorithms work well in tasks with relatively slight difference. However, when the task distribution becomes wider, it would be quite inefficient to directly…
A new method for solving complex sequential decision-making problems by decomposing them into multiple levels.
problem Sequential decision-making with natural multi-level structure.
method Multi-level meta-reinforcement learning with skill-based curriculum.
result Efficiently reduces stochasticity and policy search space, leading to fewer iterations and computations.
Credit assignment in Meta-reinforcement learning (Meta-RL) is still poorly understood. Existing methods either neglect credit assignment to pre-adaptation behavior or implement it naively. This leads to poor sample-efficiency during meta-training as well as ineffective task identification strategies. This paper provide…
The capacity of meta-learning algorithms to quickly adapt to a variety of tasks, including ones they did not experience during meta-training, has been a key factor in the recent success of these methods on few-shot learning problems. This particular advantage of using meta-learning over standard supervised or reinforce…
This paper introduces Meta-Q-Learning (MQL), a new off-policy algorithm for meta-Reinforcement Learning (meta-RL). MQL builds upon three simple ideas. First, we show that Q-learning is competitive with state-of-the-art meta-RL algorithms if given access to a context variable that is a representation of the past traject…
HyperX uses reward bonuses to enable efficient exploration in meta-learning.
problem Catastrophic failure of meta-learning with sparse rewards.
method HyperX uses novel reward bonuses to explore in approximate hyper-state space.
result HyperX meta-learns better task-exploration and adapts more successfully to new tasks.
Learning from small data sets is critical in many practical applications where data collection is time consuming or expensive, e.g., robotics, animal experiments or drug design. Meta learning is one way to increase the data efficiency of learning algorithms by generalizing learned concepts from a set of training tasks …
In this paper, we propose a novel meta-learning method in a reinforcement learning setting, based on evolution strategies (ES), exploration in parameter space and deterministic policy gradients. ES methods are easy to parallelize, which is desirable for modern training architectures; however, such methods typically req…
Minimum attention improves reinforcement learning performance in high-dimensional dynamics.
problem Improving reinforcement learning performance in high-dimensional nonlinear dynamics.
method Applying minimum attention as a regularization technique in reinforcement learning, including model-based and model-free approaches.
result Minimum attention outperforms state-of-the-art algorithms in few-shot adaptation and variance reduction.