ViZDoom competition tests AI in Doom using only visual input.
problem Creating AI bots that play Doom effectively from raw visual data.
method Multi-player deathmatch in Doom; bots make decisions based on screen buffer.
result Reinforcement learning can produce capable bots but not competitive against humans.
GANs generate DOOM levels similar to human-designed ones.
problem Generating levels similar to human-designed ones in first-person shooter games.
method Extracted features from human-designed levels, trained GANs on these features and level images, generated new levels, compared results.
result GANs can generate levels similar to human-designed ones.
Deep RL agent performs well in Doom, a complex FPS game.
problem Addressing complex environments with sparse rewards and large state spaces.
method Divide and conquer approach using unsupervised auxiliary tasks.
result Our agent performs better in unknown environments than state-of-the-art algorithms.
A number of recent approaches to policy learning in 2D game domains have been successful going directly from raw input images to actions. However when employed in complex 3D environments, they typically suffer from challenges related to partial observability, combinatorial exploration spaces, path planning, and a scarc…
SMiRL learns to minimize surprise in unstable environments, improving agent performance.
problem Learning useful behaviors in unpredictable, unstable environments.
method Alternates between learning a density model and improving policy to seek more predictable stimuli.
result SMiRL agents can play games, control robots, and navigate mazes without task-specific rewards.
Unbiased wealth exchanges always lead to inequality.
problem Understanding wealth distribution in unbiased binary exchange systems.
method Analytical demonstration of unbiased binary exchanges leading to perfect inequality.
result Any system driven by unbiased binary exchanges will reach perfect inequality and zero mobility.
Paper proves inequalities for differential forms in Euclidean and Heisenberg groups.
problem Proving inequalities for differential forms in limiting L^1 norm.
method Interior Poincaré and Sobolev inequalities, replacing L^p estimates.
result Developed inequalities for L^1 norm, including singular integral estimates.
We employ min-max methods to construct uncountably many, geometrically distinct, properly embedded geodesic lines in any asymptotically conical surface of non-negative scalar curvature, a setting where minimization schemes are doomed to fail. Our construction provides control of the Morse index of the geodesic lines we…
We present a model of predatory traders interacting with each other in the presence of a central reserve (which dissipates their wealth through say, taxation), as well as inflation. This model is examined on a network for the purposes of correlating complexity of interactions with systemic risk. We suggest the use of s…
MIME uses mutual information minimization for better exploration in environments with abrupt transitions.
problem Agents struggle at abrupt environmental transitions.
method MIME learns a latent representation without predicting future states.
result MIME outperforms surprisal-driven agents at transition boundaries.
Paper proposes a more robust deep reinforcement learning agent.
problem Creating more robust reinforcement learning agents.
method Modified A3C algorithm with dual input streams.
result Significant reduction in training parameters (30%) with improved robustness.
GNNs may be limited by graph topology, affecting their learning outcomes.
problem Understanding how graph topology influences GNN behavior and performance.
method Investigating the interaction between local topological features and GNN message-passing schemes.
result Locally similar neighborhoods can lead to consistent node representations, affecting GNN performance.
Economy is demanding new models, able to understand and predict the evolution of markets. To this respect, Econophysics is offering models of markets as complex systems, such as the gas-like model, able to predict money distributions observed in real economies. However, this model reveals some technical hitches to expl…
Learning robust value functions given raw observations and rewards is now possible with model-free and model-based deep reinforcement learning algorithms. There is a third alternative, called Successor Representations (SR), which decomposes the value function into two components -- a reward predictor and a successor ma…
Extends pretrained models with new images and anatomy.
problem Training deep learning models from scratch with large annotated datasets is infeasible and computationally limited.
method Introduces a framework for incremental learning where new information is added iteratively while preserving representative past data.
result Increased learning capacity demonstrated through comparative evaluations on MR images.
Model shows how banks' fears of future defaults can cause immediate financial stress.
problem How banks' future default worries cause immediate financial stress.
method Dynamic interbank model with endogenous distress contagion, mark-to-market valuation adjustment, forward-backward approach.
result Distress contagion acts as a stochastic volatility term leading to clustering and down-market spikes.
Economy is demanding new models, able to understand and predict the evolution of markets. To this respect, Econophysics offers models of markets as complex systems, that try to comprehend macro-, system-wide states of the economy from the interaction of many agents at micro-level. One of these models is the gas-like mo…
Study uses attention-based method to detect different types of online harassment.
problem Detecting different types of online harassment in social media content.
method Multi-attention based approach using Recurrent Neural Networks to address imbalanced data.
result Demonstrates effectiveness of attention-based mechanism for detecting various types of online harassment.
Efficiently learns object representations for FPS games.
problem Learning to play FPS games with limited training data.
method Detects salient segments, clusters them, and uses their importance for classification.
result Improves performance of DRQN by focusing on relevant object categories.
Proposes methods to compute optimal transport maps via subspace projections.
problem Computing optimal transport in high dimensions is challenging due to the curse of dimensionality.
method Develops two methods to extrapolate optimal transport plans from subspace projections to the full space.
result The best optimal transport plan is a generalization of the Knothe-Rosenblatt transport.