An agent explores indefinitely in an environment with unlimited rewards.
problem Balancing exploration and exploitation in environments with unlimited rewards.
method Simple example of an environment with unbounded rewards and optimal agent behavior.
result An optimal agent always explores to maximize rewards, regardless of accumulated knowledge.
VASE uses Bayesian neural networks to improve exploration in sparse reward environments.
problem Exploration in environments with continuous control and sparse rewards.
method VASE uses a Bayesian neural network model of the environment dynamics and variational inference to alternately update the model's accuracy and policy.
result VASE outperforms other surprise-based exploration techniques in continuous control sparse reward environments.
BYOL-Explore learns to explore visually-rich environments by predicting world dynamics.
problem Exploration in visually complex environments.
method Optimizes a single prediction loss in latent space to learn world representation, dynamics, and exploration policy.
result Achieves superhuman performance on Atari games with simpler design.
Paper tackles efficient exploration of unseen graph-structured environments.
problem Efficient exploration of unseen graph-structured environments.
method Learning to explore framework using reinforcement learning and graph-structured memory.
result Approach outperforms hand-engineered methods in software testing and real-world applications.
This paper explores how hierarchical agent policies affect exploration in goal-driven navigation environments.
problem Understanding how hierarchical agent policies influence exploration in goal-driven navigation.
method Design of EscapeRoom environments, measuring complexity with hitting times of dependency graphs, evaluating PPO and hierarchical PPO.
result Analytically estimated hitting time in goal dependency graphs is a metric of environment complexity and hierarchical approaches are necessary for complex environments.
Intrinsically motivated goal exploration processes enable agents to autonomously sample goals to explore efficiently complex environments with high-dimensional continuous actions. They have been applied successfully to real world robots to discover repertoires of policies producing a wide diversity of effects. Often th…
ExTra uses past experience to guide exploration in reinforcement learning.
problem Navigating new tasks with limited prior knowledge.
method Transfer-guided exploration using bisimulation distances and Softmax sampling.
result ExTra outperforms traditional exploration methods in gridworld environments.
DQN with model-based exploration improves learning in sparse reward environments.
problem Poor sample efficiency in sparse reward environments.
method Combines model-free and model-based approaches for better exploration.
result Improves performance in environments with sparse rewards.
This work uses model uncertainty for efficient exploration in sparse reward environments.
problem Challenging exploration in sparse reward reinforcement learning environments.
method Implicit generative modeling approach to estimate Bayesian uncertainty of the agent's belief of the environment dynamics.
result Our implicit generative model consistently outperforms competing approaches in data efficiency for exploration.
Project explores reinforcement learning solutions for sparse reward environments.
problem Difficulty in navigating environments with infrequent rewards.
method Contrast and investigate existing reinforcement learning solutions in various video games.
result Introduces a novel reinforcement learning solution combining curiosity and auxiliary tasks.
To maximize its success, an AGI typically needs to explore its initially unknown world. Is there an optimal way of doing so? Here we derive an affirmative answer for a broad class of environments.
New method uses hindsight to make exploration robust in stochastic environments.
problem Exploration in sparse-reward or reward-free environments, especially in stochastic settings.
method Learn representations of the future that capture unpredictable aspects, using them to predict and reward only the predictable parts of the world.
result Improves exploration in Atari games and Montezuma's Revenge, robust to stochasticity.
MAX uses ensemble models to efficiently explore novel situations in reinforcement learning.
problem Efficient exploration in reinforcement learning.
method Model-based active exploration using ensemble forward models and Bayesian disagreement.
result MAX is at least an order of magnitude more efficient than baselines in semi-random environments.
A method for self-supervised representation learning in partially observable environments.
problem Sparse rewards and stochasticity in partially observable environments.
method World model in latent space for estimating missing information.
result Significant improvement in exploration compared to prior work.
Enhances POLITEX for exploration in reinforcement learning with no-reward learning.
problem Learning to explore in reinforcement learning problems with no-reward.
method Modifies POLITEX to incorporate a pre-existing exploration policy.
result Achieves sublinear regret guarantees similar to POLITEX but without requiring all policies to explore.
Efficient exploration in complex environments remains a major challenge for reinforcement learning. We propose bootstrapped DQN, a simple algorithm that explores in a computationally and statistically efficient manner through use of randomized value functions. Unlike dithering strategies such as epsilon-greedy explorat…
NetHack Learning Environment (NLE) tests RL algorithms, offering scalable, complex, and challenging gameplay.
problem Challenging environments for testing RL algorithms.
method Procedurally generated, stochastic, rich, and complex NetHack environment.
result Demonstrates empirical success for early stages of NetHack using RL.
HOMER learns latent states to explore rich environments efficiently.
problem Exploration in rich observation environments with unknown latent states.
method Interleaves representation learning and strategic exploration to identify kinematic states.
result Provably efficient exploration with polynomial sample complexity in latent states and time horizon.
A new exploration method for RL using parameter space noise.
problem Improving exploration in deep reinforcement learning.
method Switching isotropic and directional exploration in parameter space with parameter space noise.
result The proposed method achieves competitive results and better performance in sparse reward environments.
AceIRL learns expert reward from active exploration.
problem Learning reward function from expert demonstrations in unknown environments.
method Active exploration to infer reward function and identify good policy.
result First approach to active IRL with sample-complexity bounds that doesn't require a generative model.
New method learns adaptive exploration strategies for dynamic tasks.
problem Learning effective exploration strategies in changing environments.
method Informed policy regularization to reduce sample complexity of RNN-based policies.
result Method learns efficient exploration strategies balancing information gathering and reward maximization.
FICM uses motion features to encourage exploration in DRL environments.
problem Exploiting novelty in environments with moving objects.
method Flow-based intrinsic curiosity module (FICM) leveraging motion features between consecutive frames.
result FICM encourages exploration in environments featuring moving objects.
This paper proposes a self-supervised exploration method using disagreement of dynamics models.
problem Efficient exploration in stochastic environments with real robots.
method Train an ensemble of dynamics models and incentivize exploration to maximize disagreement.
result Sample-efficient exploration achieved without external rewards or reinforcement learning.
New exploration bonuses improve reinforcement learning efficiency.
problem Efficient exploration in unknown environments with limited feedback.
method Improved exploration bonuses scaling with 1/n and improved stopping time analysis.
result Faster learning rates and improved sample complexity in pure-exploration settings.
Maximizes Rényi entropy for efficient exploration in reward-free RL.
problem Challenges of exploration in reward-free reinforcement learning.
method Maximizes Rényi entropy over state-action space in exploration phase; uses batch RL for planning phase.
result Effective and sample-efficient exploration leading to superior policies.
MULEX separates exploration and exploitation in reinforcement learning.
problem Balancing discovery of new rewards with past behavior in reinforcement learning.
method Disentangles exploration and exploitation by optimizing multiple losses in parallel.
result MULEX achieves sample-efficiency and robustness in a hard-exploration environment.
In many real-world scenarios, rewards extrinsic to the agent are extremely sparse, or absent altogether. In such cases, curiosity can serve as an intrinsic reward signal to enable the agent to explore its environment and learn skills that might be useful later in its life. We formulate curiosity as the error in an agen…
This research tackles balancing exploration and exploitation in deep RL for partially observable systems.
problem Balancing exploration and exploitation in deep RL for partially observable systems.
method Deployed and tested several techniques including adaptive and deterministic exploration strategies, and a modified quadratic loss function.
result Adaptive methods better approximate the trade-off between exploration and exploitation.
A new HRL algorithm learns and exploits multiple subgoals for faster exploration.
problem Sparse reward problem in reinforcement learning.
method Multi-goal HRL algorithm with Manager and Worker policies.
result Significantly improved exploration efficiency with reduced training time.
Meta-learning agents excel at rapidly learning new tasks from open-ended task distributions; yet, they forget what they learn about each task as soon as the next begins. When tasks reoccur - as they do in natural environments - metalearning agents must explore again instead of immediately exploiting previously discover…
CARL safely adapts RL agents for safety-critical tasks.
problem Safety hazards in RL for safety-critical tasks.
method CARL combines model-based RL and cautious adaptation.
result CARL achieves higher rewards with fewer failures in safety-critical tasks.
New RL method explores environments without rewards, achieving efficient policy generation.
problem Efficiently exploring unknown environments without predefined rewards.
method Optimistic value-iteration algorithm with kernel and neural function approximations.
result Achieves O ~ ( 1 / ε 2 ) \widetilde{\mathcal{O}}(1 /\varepsilon^2) O ( 1/ ε 2 ) sample complexity for generating policies or equilibria. A method for Bayes-Adaptive Deep RL using meta-learning.
problem Maximizing expected return in unknown environments with uncertainty.
method variBAD: meta-learning for approximate inference and task uncertainty.
result variBAD achieves higher online return than existing methods in MuJoCo domains.
This work learns latent representations to speed up exploration in complex environments.
problem Challenging exploration in high-dimensional state and action spaces with sparse rewards.
method Representation learning using prior experience to learn effective latent representations.
result Learned latent representations reduce the dimensionality of the search space for effective exploration.
The paper proposes an algorithm to learn efficient and effective exploration policies in reinforcement learning.
problem Balancing exploration and exploitation in reinforcement learning.
method Formalized a counterfactual metric for exploration utility and used meta-learning to learn an end-to-end exploration policy.
result Demonstrated improved performance in high-dimensional control tasks in MuJoCo simulator compared to previous methods.
Study how untrained policies explore in RL environments.
problem Challenges in reinforcement learning, especially sparse or adversarial reward structures.
method Theoretical and empirical analysis of untrained deep neural policies in a toy model.
result Untrained policies generate correlated actions and non-trivial state-visitation distributions.
Combines NES and PPO to enhance exploration in various environments.
problem Improving exploration in reinforcement learning environments.
method Parameter transfer and parameter space noise methods for combining NES and PPO.
result PPO benefits from both NES methods in discrete and continuous control tasks.
Study task-guided exploration in linear dynamical systems, improving sample complexity.
problem Efficiently learning about an environment to complete a specific task.
method Proposed a computationally efficient experiment-design based exploration algorithm.
result Optimally explores the environment, collecting precise information needed to complete the task.
A new approach for deep exploration in sparse reward reinforcement learning.
problem Slow or no learning in reinforcement learning with rare rewards.
method Long-term visitation count planning and decoupling exploration and exploitation.
result Significantly outperforms existing methods in sparse reward environments.
Optimally explores dynamical systems with varying properties using context inference.
problem Learning dynamics models for systems with varying properties.
method Formulates dynamics models as stochastic processes conditioned on a latent context variable inferred from system transitions. Uses probabilistic formulation to compute optimal action sequences for exploration.
result Demonstrates effectiveness of the method on non-linear toy-problems and reinforcement learning environments.
Hyper addresses the hyperparameter tuning challenge in RL, improving exploration efficiency and robustness.
problem Hyperparameter tuning is a significant challenge in RL, especially for curiosity-based exploration methods.
method Hyper robustly explores by effectively regularizing exploration visits and decoupling exploitation.
result Hyper is provably efficient and robust in various RL environments.
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.
GENE tackles sparse reward in RL by generating states to explore and exploit.
problem Sparse reward in reinforcement learning.
method Generative Exploration and Exploitation (GENE) method.
result GENE significantly outperforms existing methods in tasks with binary rewards.
This work designs an active world model learning system with progress-based curiosity.
problem Learning compact world models from visual exploration.
method Constructs a curious agent in a 3D environment, using γ γ γ -Progress as a curiosity signal. result The γ γ γ -Progress-driven controller outperforms state-of-the-art exploration strategies. Empowerment-driven exploration improves performance in sparse reward environments.
problem Challenges in reinforcement learning, especially in sparse reward environments.
method Formulate empowerment as mutual information between states and actions, estimate using Mutual Information Neural Estimator and forward dynamics model.
result Empowerment-driven agents significantly improve performance on Montezuma's Revenge.
BeBold improves exploration in sparse-reward tasks by regulating visitation counts.
problem Efficient exploration in deep reinforcement learning under sparse rewards.
method Regulated difference of inverse visitation counts.
result BeBold solves 12 challenging tasks in MiniGrid with fewer steps than previous state-of-the-art.
New algorithms reduce dynamic regret in non-stationary RL environments.
problem Optimizing policies in environments that change over time.
method POWER and POWER++ algorithms for policy optimization with dynamic regret analysis.
result POWER++ improves dynamic regret by actively adapting to non-stationarity.
Improves model-based control and exploration by estimating model uncertainty.
problem Inaccuracies in model predictions lead to frequent re-planning, inefficiency, and unreliability.
method Estimates model uncertainty using reconstruction error and uses it for better control and active exploration.
result Improves control performance and exploration efficiency by choosing confident model predictions and planning for high uncertainty.