Improves deep RL for partially observable environments.
problem Handling partially observable environments in deep RL.
method Action-specific Deep Recurrent Q-Network (ADRQN) architecture.
result Demonstrates effectiveness in partially observable domains.
DPFRL uses particle filters for decision making with complex visual observations.
problem Decision making with partial complex visual observations.
method Discriminative Particle Filter Reinforcement Learning (DPFRL) with a differentiable particle filter in the neural network policy.
result DPFRL outperforms state-of-the-art POMDP RL models in complex visual observation tasks.
Model-based RL learns Atari games faster with fewer interactions.
problem Efficiently learning Atari games with minimal interactions.
method Simulated Policy Learning (SimPLe) using video prediction models.
result SimPLe outperforms model-free methods in most Atari games with fewer interactions.
Agent57 beats human average on all Atari games.
problem Atari game benchmark's poor performance in challenging games.
method Trained neural network with adaptive policy selection and novel architecture.
result First deep RL agent to outperform human average on all 57 Atari games.
Visual analogies help transfer knowledge between Atari games.
problem Can visual analogies transfer knowledge between Atari games?
method Created visual analogies between pairs of Atari games and used them to train policies for one game using data from another.
result Visual analogies can be used to transfer knowledge between Atari games.
Deep RL algorithm learns human-level policies on nearly all Atari games.
problem Consistent performance on diverse Atari games.
method Addressing three key challenges: diverse reward distributions, long-term reasoning, and efficient exploration.
result Exceeds human performance on 40 out of 42 Atari games.
Proposes a new Deep Recurrent Double Q-Learning model for Atari games.
problem Improving Deep Reinforcement Learning models for Atari games.
method Integrates Double Q-Learning and Recurrent Networks (LSTM, DRQN) for Atari games.
result Demonstrates improved performance in Atari games compared to existing models.
Low precision RL distillation enables real-time game play on neuromorphic hardware.
problem Limited use of low precision networks in reinforcement learning.
method Policy distillation from high precision to low precision networks.
result Low precision distillation enables real-time game play on low-power hardware.
Method learns state representations without supervision for Atari games.
problem Learning state representations without supervision.
method Maximizes mutual information across features of neural encoder.
result New benchmark for evaluating representation learning models.
A new RL method boosts exploration efficiency in Atari games and driving simulators.
problem Efficient exploration in reinforcement learning environments.
method A two-component approach: decaying schedule and upper quantile bonus.
result Significantly outperforms QR-DQN in Atari games and near-optimal safety in CARLA.
Combines human demonstrations and preferences to learn rewards for reinforcement learning.
problem Learning reward functions for complex real-world reinforcement learning problems.
method Trains a deep neural network to model reward functions from human demonstrations and preferences, then uses the model to train a DQN agent.
result Achieves superhuman performance on 2 Atari games without using game rewards.
A new method for exploration in reinforcement learning improves performance on Atari games.
problem Improving exploration in reinforcement learning algorithms, especially for complex games.
method Random Network Distillation (RND) bonus combined with flexible reward combination.
result Significant progress on hard exploration Atari games, including Montezuma's Revenge.
Develops a deep metric learning approach for detecting bugs in video games.
problem Automated detection of bugs in video games.
method State-State Siamese Networks (S3N) for deep metric learning.
result S3N learns meaningful embeddings to identify various types of bugs.
Enhances deep reinforcement learning with object recognition.
problem Few works consider object characteristics in deep reinforcement learning.
method Proposes a novel method to incorporate object recognition into deep reinforcement learning models.
result Shows state-of-the-art results on Atari games.
A new method for reinforcement learning using quantile regression.
problem Improving reinforcement learning algorithms for better performance.
method Using quantile regression to approximate the full quantile function for state-action return distributions.
result Improved performance on Atari games, demonstrating the effectiveness of the method.
Large-scale eye-tracking dataset for Atari games.
problem Improving AI decision-making through human eye-tracking data.
method Recorded 117 hours of gameplay with eye movements from 20 Atari games.
result Human gameplay decisions and scores comparable to human records.
Reinforcement learning is concerned with identifying reward-maximizing behaviour policies in environments that are initially unknown. State-of-the-art reinforcement learning approaches, such as deep Q-networks, are model-free and learn to act effectively across a wide range of environments such as Atari games, but requ…
DreamerV2 learns Atari game behaviors from a world model, achieving human-level performance.
problem Learning complex behaviors in Atari games from limited data.
method DreamerV2 uses a world model with discrete representations to predict behaviors in a compact latent space.
result Achieves human-level performance on 55 Atari tasks.
Video games improve vehicle routing performance.
problem Optimizing vehicle routes with unpredictable passenger requests.
method Replaced vehicle routing with a game, trained agents to play.
result General game-playing agents outperform traditional methods.
This work makes deep reinforcement learning more transparent by visualizing the decision-making process.
problem Making deep reinforcement learning models transparent and explaining their decisions.
method Proposes to visualize the evidence on which the agent bases its decision.
result Makes deep reinforcement learning more transparent and interpretable.
Tiny neural networks learn Atari games with just 6 neurons.
problem Understanding and simplifying complex vision-based decision-making tasks.
method Separate learning of state representations and policies, using novel encoding algorithms.
result 6-neuron neural networks achieve comparable results to state-of-the-art methods.
A new RL method improves performance on Atari games without complex techniques.
problem Improving reinforcement learning performance on Atari games.
method Adding scaled log-policy to immediate reward in DQN.
result The modified DQN outperforms Rainbow on Atari games.
Researchers create a flickering attack to fool video recognition networks.
problem Adversarial manipulation of video classification networks.
method Introducing a flickering temporal perturbation to fool video classifiers.
result Achieved high fooling ratio and temporal-invariant perturbation.
Deep learning improves reinforcement learning in video games.
problem Challenges in reinforcement learning with high-dimensional inputs.
method Used deep Q-network and batch normalization to improve reinforcement learning.
result Some agents learned to play T-rex Runner better than human experts.
New method learns Atari game Montezuma's Revenge from a single demonstration.
problem Learning from sparse rewards in complex exploration tasks.
method Maximizing rewards directly from a single demonstration state, combined with off-the-shelf reinforcement learning.
result Trained agent achieves high-score of 74,500 in Montezuma's Revenge.
A human-like strategy improves DRL performance in Atari games.
problem Lack of exploration in DRL for high-dimensional problems.
method Mixed strategy approach mimicking human behavior.
result Higher maximum score probability achieved in Breakout game.
AG-RL uses action grammars to improve reinforcement learning efficiency.
problem Improving sample efficiency in reinforcement learning.
method Integrates action grammars into reinforcement learning algorithms to enhance performance.
result Significant improvement in performance across multiple Atari games.
MuZero learns models to master complex games without domain knowledge.
problem Mastering complex, real-world domains with unknown dynamics.
method Combining tree-based search with learned models.
result Achieves superhuman performance in diverse domains.
This work compresses reinforcement learning models for Atari games, improving localization.
problem Expensive deep neural networks in reinforcement learning.
method Model compression, global max-pooling, Actor-Mimic, weakly supervised localization.
result Compression reduces model size to 3% of original, enabling object localization.
Paper presents a new method for Bayesian deep learning that scales to Atari games.
problem Training neural networks on complex environments like Atari games is challenging.
method Adapted temporal difference Q-learning to work with Bayesian inference.
result TAGI allows for analytical inference of neural network parameters, achieving performance comparable to gradient-based methods.
The study explores when parametric models enhance reinforcement learning, validating a hypothesis on Atari games.
problem When and how to use parametric models in reinforcement learning.
method Comparison of parametric models and experience replay, validating a hypothesis on Atari games.
result Replay-based algorithms can be competitive or superior to model-based algorithms under suitable conditions.
Paper proposes a new method for better estimating continuous distributions in RL.
problem Challenges in parameterizing estimated distributions for better approximation of true continuous distribution.
method Proposes fully parameterized quantile function with fraction and value networks.
result Significantly outperforms existing distributional RL algorithms on 55 Atari Games.
Improved deep Q-learning with SVRG reduces variance and stabilizes training.
problem Excessive variance in gradient estimation hinders deep Q-learning performance.
method Utilized stochastic variance reduced gradient (SVRG) techniques.
result Significantly improved performance on 18 out of 20 Atari games compared to baseline methods.
Bayesian REX learns Atari games from demonstrations efficiently.
problem Bayesian reward learning for complex control problems is computationally intractable.
method Bayesian Reward Extrapolation (Bayesian REX) pre-trains a low-dimensional feature encoding and uses preferences to perform fast Bayesian inference.
result Bayesian REX learns Atari games from demonstrations in 5 minutes, competitive with state-of-the-art methods.
New Soft Actor-Critic for discrete actions.
problem Applying reinforcement learning to games with discrete actions.
method Derived an alternative Soft Actor-Critic for discrete actions.
result Competitive with tuned model-free state-of-the-art on Atari games.
Approach enables reinforcement learning agents to generalize from a single task to new tasks.
problem Catastrophic forgetting in reinforcement learning when facing a new task.
method Adversarial objective and semisupervised learning.
result The approach outperforms common baselines on Atari games.
Paper proposes an RL algorithm to ensure policy performance guarantees.
problem Lack of performance guarantees for RL policies compared to baselines.
method Online model-free algorithm that ensures conservative exploration.
result Regret bound of i l d e O ( T ) ilde{\mathcal{O}}(\sqrt{T}) i l d e O ( T ) for both discrete and continuous spaces. SIL learns to repeat past good decisions for better exploration.
problem Improving exploration in reinforcement learning environments.
method Self-Imitation Learning (SIL) is a simple off-policy actor-critic algorithm.
result SIL significantly improves A2C on Atari games and is competitive with state-of-the-art methods.
Generative deep learning creates counterfactual states to explain Atari agent decisions.
problem Difficulty in explaining deep reinforcement learning agent decisions to humans.
method Generative deep learning to create counterfactual states.
result Counterfactual states help non-expert participants understand Atari agent decision-making.
DVRL learns a generative model for partially observable environments.
problem Learning in partially observable environments with unknown models.
method Introduces a deep variational approach to learn a generative model and perform inference.
result DVRL outperforms previous methods in partially observable environments.
Adapting momentum from optimization to reinforcement learning.
problem Improving the convergence and stability of reinforcement learning algorithms.
method Introducing Momentum Value Iteration (MoVI) by incorporating an average of consecutive state-action value functions, inspired by the concept of momentum in optimization.
result MoVI improves the convergence and stability of reinforcement learning algorithms, as demonstrated by experiments on Atari games.
CNN-AIRL improves video game performance using expert demonstrations.
problem Designing reward functions for complex video games is difficult.
method Adversarial IRL with CNNs, autoencoder state representation, reward normalization.
result Achieves high-level performance on Catcher game, outperforming baseline.
Study finds reinforcement learning performance plateaus due to environmental interference.
problem Catastrophic interference hinders sample efficiency in reinforcement learning.
method Empirical study in ALE, controlled experiments, analysis of prediction errors.
result Interference causes performance plateaus and degrades policies used to reach them.
Improved robustness of RL policies in SNNs for Atari games.
problem High sensitivity of RL policies to noisy input data.
method Conversion of Q-Learning NNs trained using RL to Spiking Neural Networks (SNNs).
result Improved robustness of SNNs to occlusion in input images.
Achieving efficient and scalable exploration in complex domains poses a major challenge in reinforcement learning. While Bayesian and PAC-MDP approaches to the exploration problem offer strong formal guarantees, they are often impractical in higher dimensions due to their reliance on enumerating the state-action space.…
Scaling up model and data size improves imitation learning in single-agent games.
problem Limited recovery of expert behavior in single-agent games using imitation learning.
method Investigate the effect of scaling model and data size on imitation learning performance.
result IL loss and mean return scale with compute budget, resulting in power laws.
A new reward learning module improves imitation learning in high-dimensional environments.
problem Challenges in high-dimensional environments for imitation learning.
method Generative model to generate intrinsic reward signals.
result Our method outperforms state-of-the-art IRL methods on Atari games.
NoisyNet uses stochastic weights to enhance exploration in reinforcement learning.
problem Improving exploration in reinforcement learning agents.
method Parametric noise added to weights, parameters learned with gradient descent.
result NoisyNet improves performance on Atari games, sometimes reaching super-human levels.