Max entropy exploration guides reinforcement learning agents to pursue achievable goals.
problem Achieving distant test-time goals in long-horizon tasks.
method Optimize entropy of historical achieved goals by focusing on sparsely explored areas.
result Order of magnitude better sample efficiency on long-horizon multi-goal tasks.
Aims to optimize goal sampling in deep reinforcement learning.
problem The sampling of goals affects deep reinforcement learning performance.
method Curriculum goal masking method to focus on medium difficulty goals.
result Focusing on medium difficulty goals leads to better learning performance.
This work learns a distance function for goal-conditioned RL without prior knowledge.
problem Learning a distance function for goal-conditioned reinforcement learning without prior knowledge.
method Self-supervised approach to learn distance function in terms of actions needed to reach a goal.
result Solves complex tasks in three scenarios without prior domain knowledge.
Deep RL optimizes goal-based investing strategies.
problem Optimizing investment strategies for achieving financial goals.
method Novel deep reinforcement learning approach for goal-based investing.
result Superior performance compared to benchmarks.
Agent learns goals and rewards through language and curiosity.
problem Autonomous agents lack intrinsic motivations and reward functions.
method LE2 algorithm using NL interactions and intrinsic motivations.
result Agent autonomously discovers and grounds goals in real behavior.
This work improves Hindsight Learning for goal-directed tasks in reinforcement learning.
problem Sparse reward problems in reinforcement learning, especially goal-directed tasks.
method Improves Hindsight Experience Replay and Hindsight Policy Gradients for robotic tasks.
result Improved learning in Hindsight Experience Replay and Hindsight Policy Gradients.
Adapts Floyd-Warshall algorithm for RL to improve multi-goal task learning.
problem Limited transfer of learned information in model-free RL for dynamic goal tasks.
method Adapts Floyd-Warshall algorithm for RL to learn goal-conditioned action-value functions.
result FWRL achieves higher reward strategies in multi-goal tasks with fewer samples.
New method learns optimal environment and goal difficulty for reinforcement learning.
problem Lack of robust transfer in reinforcement learning.
method Self-Supervised Active Domain Randomization (SS-ADR).
result Optimal domain randomization strategy improves transfer in goal-directed tasks.
The paper proposes a method for a robot to learn skills from imagined goals.
problem Training robots to perform a wide range of tasks with raw sensory input.
method Combining unsupervised representation learning and reinforcement learning of goal-conditioned policies.
result The method learns skills that can operate on raw image observations and outperforms prior techniques.
A novel RL objective and prioritization framework improve performance and sample-efficiency in multi-goal tasks.
problem Learning diverse goals in multi-goal reinforcement learning.
method Maximum entropy regularization for objective and prioritization framework.
result Promising improvements in performance and sample-efficiency on multi-goal robotic tasks.
Curiosity-driven exploration learns disentangled goal spaces for efficient complex environments.
problem Efficient exploration in complex environments with high-dimensional continuous actions.
method Learned disentangled goal spaces to reflect the environment's structure and maximize learning progress.
result Disentangled goal spaces lead to better exploration performances than entangled goal spaces.
A method for setting up an automatic curriculum for reinforcement learning tasks.
problem Improving sample efficiency in multi-task reinforcement learning.
method Propose a goal proposal module that prioritizes goals maximizing epistemic uncertainty of the Q-function.
result Significant performance gains over current methods in 13 multi-goal robotic tasks and 5 navigation tasks.
The paper explores updating multiple goals in reinforcement learning with neural networks.
problem Training agents to achieve mastery in complex, non-tabular domains.
method Three extensions of Kaelbling's all-goals updating approach using deep neural networks.
result Many-goals updating can be used to pre-train networks and improve learning on a single task.
Skew-Fit learns goal distributions for reinforcement learning, enabling state coverage.
problem Learning flexible skills without manual reward design.
method Formal exploration objective for maximizing state coverage, combined with entropy maximization.
result Skew-Fit converges to a uniform state distribution, enabling new skill learning.
CM3 learns multi-agent cooperation by first achieving individual goals.
problem Cooperative multi-agent control with multiple goals and interactions.
method Two-stage curriculum: first learn individual goals, then cooperation; new policy gradient with credit function.
result CM3 learns faster on multi-goal multi-agent problems than existing algorithms.
A novel framework uses goal-conditioned reinforcement learning to generate diverse samples.
problem Generating high-quality, diverse samples from generative models.
method Two agents: GC-agent learns to reconstruct the training set, S-agent learns to imitate GC-agent without knowing the goals.
result Empirically, the method generates diverse and high-quality samples in image synthesis.
Algorithm learns goals without rewards, controls environments.
problem Learning control without supervised rewards.
method Dual optimization of policy and reward function.
result Agent learns to achieve goals in diverse domains.
A new EM framework for goal-conditioned RL improves performance on sparse reward tasks.
problem Handling sparse rewards in goal-conditioned reinforcement learning.
method A graphical model framework with an EM algorithm that includes a learning-in-hindsight E-step and a supervised M-step.
result hEM significantly outperforms model-free baselines on goal-conditioned benchmarks with sparse rewards.
Automatically generates curricula for reinforcement learning agents.
problem Learning in dynamic, sparse reward environments.
method Setter-solver paradigm focusing on goal validity, feasibility, and coverage.
result Demonstrated success in 2D and 3D environments with varying goals.
Paper proposes Imitative Models combining IL and planning for flexible goal achievement.
problem Difficult to direct IL to arbitrary goals and specify reward functions for goal-directed planning.
method Imitative Models are probabilistic predictive models that plan interpretable expert-like trajectories.
result Imitative Models outperform IL and planning approaches in a dynamic autonomous driving task.
Model learns sub-goals and low-level policies for hierarchical reinforcement learning.
problem Determining appropriate low-level policies in hierarchical reinforcement learning.
method Unsupervised learning scheme based on asymmetric self-play.
result Obtains performance gains over non-hierarchical approaches.
Robotic arm learns to manipulate a ball by choosing goals from learned experience.
problem Efficient discovery of skills for long-living autonomous agents without supervision.
method Intrinsically motivated goal exploration using learned goal spaces from deep representation learning.
result Recent results show applicability of learned goal spaces on real-world robotic tasks.
HGG generates goals to improve sample efficiency in robotic tasks.
problem Efficiency in reinforcement learning with sparse reward signals.
method Generates valuable hindsight goals for reinforcement learning.
result Significantly improved sample efficiency over HER.
A new trajectory representation method for AI problems.
problem Trajectory prediction and optimization in AI problems.
method Sub-goal trees, recursively partitioning trajectories into sub-segments.
result Sub-goal trees predict trajectories faster and more accurately.
Paper proposes a method to learn goal-reaching behaviors from scratch using imitation learning.
problem Current reinforcement learning algorithms are brittle and require expert demonstrations.
method Iterated supervised learning where agents relabel and imitate generated trajectories.
result Improved goal-reaching performance and robustness over current RL algorithms.
This paper proposes a method to learn from expert trajectories by decomposing tasks into sub-goals.
problem Learning complex goal-oriented tasks with sparse rewards and limited samples.
method The approach uses expert trajectories to decompose tasks into sub-goals, learning an extrinsic reward function and modulating sub-goal predictions.
result The method alleviates errors in imitation learning and solves complex tasks that other methods cannot.
ACTRCE uses natural language to improve reinforcement learning performance.
problem Sparse reward in reinforcement learning.
method Extends HER framework with natural language goal representation.
result ACTRCE can solve challenging 3D navigation tasks and generalize to unseen instructions.
Physics-informed GCRL tackles sparse feedback learning with hybrid dynamics.
problem Sparse feedback learning with high-dimensional, hybrid, or contact-dependent dynamics.
method Introduces physics-informed inductive biases into goal-conditioned value learning.
result Contact-rich manipulation tasks degrade existing Pi-GCRL methods.
C-Learning estimates reachability over time to solve multi-goal tasks.
problem Multi-goal reaching challenges in reinforcement learning.
method Cumulative accessibility functions and recurrence relations.
result Optimal cumulative accessibility functions are monotonic in horizon.
AMIGo uses adversarial intrinsic goals to teach RL agents new skills.
problem Learning in sparse reward environments.
method Adversarial intrinsic goals to generate a curriculum for a student policy.
result AMIGo enables agents to learn new skills without extrinsic rewards.
New approach to goal-based investing using hedging and reinforcement learning.
problem Maximizing probability of reaching investment goals with varying risk aversion.
method Lower partial moments, quantile hedging, efficient hedging, reinforcement learning.
result Optimal investment policies for goal-based investing are equivalent.
This work improves imitation learning and goal-conditioned RL by estimating value densities.
problem Effective solutions for imitation and goal-conditioned reinforcement learning require reliably reaching specified states or demonstrations.
method The approach uses recent advances in density estimation to learn value functions efficiently and without hindsight bias.
result The method achieves state-of-the-art demonstration sample-efficiency in imitation learning and is both efficient and bias-free in goal-conditioned reinforcement learning.
Eikonal-Constrained QRL improves goal-reaching in reinforcement learning.
problem Reward design and out-of-distribution generalization in reinforcement learning.
method Eikonal-Constrained Quasimetric Reinforcement Learning (Eik-QRL) using the Eikonal PDE.
result Eik-QRL achieves state-of-the-art performance in offline goal-conditioned navigation and manipulation tasks.
Unified algorithm tackles various RL goals like reward-free and preference-based learning.
problem Unified approach to multiple RL learning goals.
method Decision-Estimation Coefficient (DEC) framework.
result Unified algorithm handles various learning goals with a single framework.
Improves RL planning by proposing sub-goals hierarchically.
problem Sequential planning assumption in RL.
method Divide-and-Conquer Monte Carlo Tree Search (DC-MCTS).
result Improves navigation and control tasks.
UPNs embed planning within a goal-directed policy for effective visuomotor control.
problem Learning abstract representations for visuomotor control and generalization.
method Differentiable planning within a latent space, gradient descent trajectory optimization, end-to-end learning of representations.
result UPNs can transfer visuomotor planning strategies across robots with different morphologies and actuation capabilities.
DSE learns transferable skills across changing dynamics and goals.
problem Learning transferable skills across different reinforcement learning tasks.
method Variational inference for multi-task reinforcement learning with shared and task-specific latent spaces.
result Policies can generalize to unseen dynamics and goals conditions.
The paper improves HER by prioritizing virtual goals and removing misleading samples.
problem Sparse reward functions in reinforcement learning.
method Prioritizing virtual goals based on instructiveness and removing misleading samples.
result Significant improvement in success rate and sample efficiency.
Generative neural nets learn deep policies conditioned on goals.
problem Learning optimal policies for specific goals in reinforcement learning.
method Goal-conditioned neural nets that generate deep neural policies.
result Single learned policy generator can achieve any desired return.
A novel approach learns goal-conditioned policies for locomotion using batch RL.
problem Training goal-conditioned policies for rotation invariant locomotion.
method Data augmentation and Siamese framework for invariance.
result Our approach outperforms existing RL algorithms on 3D locomotion agents.
Improves reinforcement learning for complex tasks with sparse feedback.
problem Learning optimal policies from sparse feedback is challenging.
method Three algorithms based on Hindsight Experience Replay (HER) to improve performances.
result Vast improvement in final success rate and sample efficiency.
Convolutional networks improve reinforcement learning for navigating all goals.
problem Expensive parallel updates limit reinforcement learning to small tabular cases.
method Use convolutional neural networks to generate Q-values and updates for all goals simultaneously.
result Demonstrated improved accuracy and generalization on various environments.
Study combines chit-chat and goal-oriented dialogue in fantasy games.
problem Combining naturalistic chit-chat with goal-oriented tasks in fantasy games.
method Trained a goal-oriented model with reinforcement learning against an imitation-learned chit-chat model using two approaches.
result Both models outperform a baseline and can converse naturally to achieve goals.
PlanGAN uses GANs to plan efficient trajectories for multi-goal tasks in sparse reward environments.
problem Learning with sparse rewards in multi-goal environments.
method PlanGAN combines GANs to generate trajectories leading to specified goals, then combines these into a planning algorithm.
result PlanGAN achieves comparable performance to model-free RL but is 4-8 times more sample efficient.
A new approach uses backwards induction to accelerate reinforcement learning.
problem Training reinforcement learning agents to discover goals without supervision.
method Train model to predict backwards steps from known goal states.
result Empirically shows better performance than standard DDQN.
LEXA learns to discover and achieve goals in unseen environments.
problem Learning to solve diverse tasks in complex visual environments without supervision.
method LEXA learns a world model from image inputs and uses it to train an explorer and an achiever policy from imagined rollouts.
result LEXA solves tasks specified as goal images zero-shot without additional learning.
DAGR improves navigation by refining goal representations conditioned on the current state.
problem Goal-conditioned reinforcement learning lacks state awareness, leading to inefficient policy recovery.
method DAGR refines static goal embeddings into state-conditioned ones using gated cross-attention with a state-goal discrepancy map.
result DAGR improves navigation tasks on OGBench, matching or outperforming base methods.
OptiGAN uses GAN and RL to optimize sequence generation for specific goals.
problem Challenging in sequence generation tasks to generate sequences with specific desired goals.
method Integrates GAN and RL to optimize desired goal scores using policy gradients.
result Achieves higher desired scores in text and real-valued sequence generation.