A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Abstract MDPs enable strategic exploration and fast reward transfer in complex environments.
Algorithm improves multi-armed bandit performance by transferring reward samples.
New algorithms improve multi-task bandit performance by transferring reward samples.
This work improves transferability of rewards inferred from expert demonstrations.
Paper improves AIRL by enhancing policy imitation and addressing reward recovery issues.
New framework explains fast transfer of hyperparameters across model scales.
Paper proposes operator deep Q-learning for quick reward adaptation.
Develops HMRL for sparse reward RL problems, improving meta policy efficiency and transferability.
Paper analyzes AIRL in high-dimensional spaces using random matrix theory.
This paper explores how imperfect reward models can improve online RLHF.
Current reinforcement learning (RL) methods can successfully learn single tasks but often generalize poorly to modest perturbations in task domain or training procedure. In this work, we present a decoupled learning strategy for RL that creates a shared representation space where knowledge can be robustly transferred. …
Curriculum learning has been successfully used in reinforcement learning to accelerate the learning process, through knowledge transfer between tasks of increasing complexity. Critical tasks, in which suboptimal exploratory actions must be minimized, can benefit from curriculum learning, and its ability to shape explor…
New approach transfers rewards learned in one environment to reinforcement learning in a new environment.
Task-specific scores are often used to optimize for and evaluate the performance of conditional text generation systems. However, such scores are non-differentiable and cannot be used in the standard supervised learning paradigm. Hence, policy gradient methods are used since the gradient can be computed without requiri…
Bayesian REX learns Atari games from demonstrations efficiently.
AIRL learns robust, generalizable reward functions from demonstrations.
FAST improves fast and stable task adaptation in DNNs.
Study shows fast rates for inverse reinforcement learning with linear rewards.
SF-DQN improves RL transfer by learning successor features.
Paper tackles transfer RL under unobserved context, developing methods to reduce bias.
Reinforcement learning is a promising framework for solving control problems, but its use in practical situations is hampered by the fact that reward functions are often difficult to engineer. Specifying goals and tasks for autonomous machines, such as robots, is a significant challenge: conventionally, reward function…
Improves imitation learning in RL by learning reward function efficiently.
A key question in Reinforcement Learning is which representation an agent can learn to efficiently reuse knowledge between different tasks. Recently the Successor Representation was shown to have empirical benefits for transferring knowledge between tasks with shared transition dynamics. This paper presents Model Featu…
Given a set of heterogeneous source datasets with their classifiers, how can we quickly find the most useful source dataset for a specific target task? We address the problem of measuring transferability between source and target datasets, where the source and the target have different feature spaces and distributions.…
Behavior Transfer improves reinforcement learning by leveraging pre-trained policies.
Transfer and adaptation to new unknown environmental dynamics is a key challenge for reinforcement learning (RL). An even greater challenge is performing near-optimally in a single attempt at test time, possibly without access to dense rewards, which is not addressed by current methods that require multiple experience …
Physics-informed neural networks simulate radiative transfer efficiently.
We consider the task of Inverse Reinforcement Learning in Contextual Markov Decision Processes (MDPs). In this setting, contexts, which define the reward and transition kernel, are sampled from a distribution. In addition, although the reward is a function of the context, it is not provided to the agent. Instead, the a…
One question central to Reinforcement Learning is how to learn a feature representation that supports algorithm scaling and re-use of learned information from different tasks. Successor Features approach this problem by learning a feature representation that satisfies a temporal constraint. We present an implementation…
New RL method MAC improves performance in sparse reward settings.
RL agents learn from a few tasks to generalize to new ones.
We present a method for fast training of vision based control policies on real robots. The key idea behind our method is to perform multi-task Reinforcement Learning with auxiliary tasks that differ not only in the reward to be optimized but also in the state-space in which they operate. In particular, we allow auxilia…
Transfer learning across different reinforcement learning (RL) tasks is becoming an increasingly valuable area of research. We consider a goal-based multi-task RL framework and mechanisms by which previously solved tasks can reduce sample complexity and regret when the agent is faced with a new task. Specifically, we i…
Reinforcement learning in complex environments is a challenging problem. In particular, the success of reinforcement learning algorithms depends on a well-designed reward function. Inverse reinforcement learning (IRL) solves the problem of recovering reward functions from expert demonstrations. In this paper, we solve …
Calculates local Granger causality for Gaussian and nonlinear systems.
Researchers use DT to transfer policies from one environment to another using causal reasoning.
Scalable model for slate recommendation learns reward probabilities.
SARA uses similarity to learn rewards robustly and adaptively.
New algorithms for multivariate RL improve decision-making in complex systems.
We consider a problem of learning the reward and policy from expert examples under unknown dynamics. Our proposed method builds on the framework of generative adversarial networks and introduces the empowerment-regularized maximum-entropy inverse reinforcement learning to learn near-optimal rewards and policies. Empowe…
This paper explores the possibility of near-optimally solving multi-agent, multi-task NP-hard planning problems with time-dependent rewards using a learning-based algorithm. In particular, we consider a class of robot/machine scheduling problems called the multi-robot reward collection problem (MRRC). Such MRRC problem…
A new reward shaping method balances learning efficiency and effectiveness for robot manipulation.
A common challenge in reinforcement learning is how to convert the agent's interactions with an environment into fast and robust learning. For instance, earlier work makes use of domain knowledge to improve existing reinforcement learning algorithms in complex tasks. While promising, previously acquired knowledge is of…
Many cooperative multiagent reinforcement learning environments provide agents with a sparse team-based reward, as well as a dense agent-specific reward that incentivizes learning basic skills. Training policies solely on the team-based reward is often difficult due to its sparsity. Furthermore, relying solely on the a…
Arbitrary style transfer is an important problem in computer vision that aims to transfer style patterns from an arbitrary style image to a given content image. However, current methods either rely on slow iterative optimization or fast pre-determined feature transformation, but at the cost of compromised visual qualit…
We seek to align agent behavior with a user's objectives in a reinforcement learning setting with unknown dynamics, an unknown reward function, and unknown unsafe states. The user knows the rewards and unsafe states, but querying the user is expensive. To address this challenge, we propose an algorithm that safely and …
Reward shaping is one of the most effective methods to tackle the crucial yet challenging problem of credit assignment in Reinforcement Learning (RL). However, designing shaping functions usually requires much expert knowledge and hand-engineering, and the difficulties are further exacerbated given multiple similar tas…
In this work, we evaluate adversarial robustness in the context of transfer learning from a source trained on CIFAR 100 to a target network trained on CIFAR 10. Specifically, we study the effects of using robust optimisation in the source and target networks. This allows us to identify transfer learning strategies unde…