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.
LiDER refreshes past experiences in RL by dreaming about them.
New method learns policies from past data.
In continual learning, the learner faces a stream of data whose distribution changes over time. Modern neural networks are known to suffer under this setting, as they quickly forget previously acquired knowledge. To address such catastrophic forgetting, many continual learning methods implement different types of exper…
Despite huge success, deep networks are unable to learn effectively in sequential multitask learning settings as they forget the past learned tasks after learning new tasks. Inspired from complementary learning systems theory, we address this challenge by learning a generative model that couples the current task to the…
The paper clusters hypergraphs to find diverse and experienced groups based on past experiences.
Doctors often rely on their past experience in order to diagnose patients. For a doctor with enough experience, almost every patient would have similarities to key cases seen in the past, and each new patient could be viewed as a mixture of these key past cases. Because doctors often tend to reason this way, an efficie…
BAM integrates new data while selectively remembering past observations.
Experience replay enables reinforcement learning agents to memorize and reuse past experiences, just as humans replay memories for the situation at hand. Contemporary off-policy algorithms either replay past experiences uniformly or utilize a rule-based replay strategy, which may be sub-optimal. In this work, we consid…
Estimates long-term effects using past experiments as instruments with many weak instruments.
Soft Actor-Critic (SAC) is an off-policy actor-critic deep reinforcement learning (DRL) algorithm based on maximum entropy reinforcement learning. By combining off-policy updates with an actor-critic formulation, SAC achieves state-of-the-art performance on a range of continuous-action benchmark tasks, outperforming pr…
Neural model uses deductive database to predict events from past patterns.
Experience replay (ER) is a fundamental component of off-policy deep reinforcement learning (RL). ER recalls experiences from past iterations to compute gradient estimates for the current policy, increasing data-efficiency. However, the accuracy of such updates may deteriorate when the policy diverges from past behavio…
We consider the problem of building a state representation model for control, in a continual learning setting. As the environment changes, the aim is to efficiently compress the sensory state's information without losing past knowledge, and then use Reinforcement Learning on the resulting features for efficient policy …
This paper proposes Self-Imitation Learning (SIL), a simple off-policy actor-critic algorithm that learns to reproduce the agent's past good decisions. This algorithm is designed to verify our hypothesis that exploiting past good experiences can indirectly drive deep exploration. Our empirical results show that SIL sig…
VRER selectively reuses past observations to reduce variance in policy optimization.
Reinforcement learning with sparse rewards is challenging because an agent can rarely obtain non-zero rewards and hence, gradient-based optimization of parameterized policies can be incremental and slow. Recent work demonstrated that using a memory buffer of previous successful trajectories can result in more effective…
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…
We consider the generic approach of using an experience memory to help exploration by adapting a restart distribution. That is, given the capacity to reset the state with those corresponding to the agent's past observations, we help exploration by promoting faster state-space coverage via restarting the agent from a mo…
After learning a concept, humans are also able to continually generalize their learned concepts to new domains by observing only a few labeled instances without any interference with the past learned knowledge. In contrast, learning concepts efficiently in a continual learning setting remains an open challenge for curr…
ReaPER improves learning efficiency by prioritizing reliable experiences.
AdaX improves Adam by exponentially accumulating past gradients, leading to better performance in machine learning tasks.
Learning long-term dependencies in extended temporal sequences requires credit assignment to events far back in the past. The most common method for training recurrent neural networks, back-propagation through time (BPTT), requires credit information to be propagated backwards through every single step of the forward c…
Improved Politex algorithm reduces regret bound to O(√T) with experience replay.
New framework for choosing optimal proxy metrics from past experiments.
MO2 learns useful behaviours from past experience for new tasks.
Experience replay is widely used in deep reinforcement learning algorithms and allows agents to remember and learn from experiences from the past. In an effort to learn more efficiently, researchers proposed prioritized experience replay (PER) which samples important transitions more frequently. In this paper, we propo…
We analyze a controlled price formation experiment in the laboratory that shows evidence for bubbles. We calibrate two models that demonstrate with high statistical significance that these laboratory bubbles have a tendency to grow faster than exponential due to positive feedback. We show that the positive feedback ope…
SynthER uses generative models to augment limited RL experience.
The proliferation of automated inference algorithms in Bayesian statistics has provided practitioners newfound access to fast, reproducible data analysis and powerful statistical models. Designing automated methods that are also both computationally scalable and theoretically sound, however, remains a significant chall…
AdEMAMix optimizer improves model performance and convergence speed.
Develops RL algorithm for lifelong non-stationary environments.
Knowledge graph reasoning is a critical task in natural language processing. The task becomes more challenging on temporal knowledge graphs, where each fact is associated with a timestamp. Most existing methods focus on reasoning at past timestamps and they are not able to predict facts happening in the future. This pa…
GBML with deep nets converges globally and generalizes well.
Sparse reward problems are one of the biggest challenges in Reinforcement Learning. Goal-directed tasks are one such sparse reward problems where a reward signal is received only when the goal is reached. One promising way to train an agent to perform goal-directed tasks is to use Hindsight Learning approaches. In thes…
The paper tackles intervention generalization using factor graph models.
Paper outlines a new mathematical language for experiments.
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…
All people have to make risky decisions in everyday life. And we do not know how true they are. But is it possible to mathematically assess the correctness of our choice? This article discusses the model of decision making under risk on the example of project management. This is a game with two players, one of which is…
How do macro-financial shocks affect investor behavior and market dynamics? Recent evidence on experience effects suggests a long-lasting influence of personally experienced outcomes on investor beliefs and investment, but also significant differences across older and younger generations. We formalize experience-based …
SIBRE boosts reinforcement learning convergence by rewarding improvement over past performance.
The study learns neural update rules by remembering past experiences.
First-order optimization algorithms have been proven prominent in deep learning. In particular, algorithms such as RMSProp and Adam are extremely popular. However, recent works have pointed out the lack of ``long-term memory" in Adam-like algorithms, which could hamper their performance and lead to divergence. In our s…
Deep reinforcement learning methods attain super-human performance in a wide range of environments. Such methods are grossly inefficient, often taking orders of magnitudes more data than humans to achieve reasonable performance. We propose Neural Episodic Control: a deep reinforcement learning agent that is able to rap…
We propose a policy improvement algorithm for Reinforcement Learning (RL) which is called Rerouted Behavior Improvement (RBI). RBI is designed to take into account the evaluation errors of the Q-function. Such errors are common in RL when learning the -value from finite past experience data. Greedy policies or even …
Traditional recommendation systems rely on past usage data in order to generate new recommendations. Those approaches fail to generate sensible recommendations for new users and items into the system due to missing information about their past interactions. In this paper, we propose a solution for successfully addressi…
A new spectrum recovers cobordism cut and paste groups of manifolds with boundary.
EvoRate metric assesses learnability of sequential data by measuring predictive information.
Modeling a temporal process as if it is Markovian assumes the present encodes all of the process's history. When this occurs, the present captures all of the dependency between past and future. We recently showed that if one randomly samples in the space of structured processes, this is almost never the case. So, how d…