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.
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.
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.
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.
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.
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.
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.
Sample-Rank simplifies MO recommendations by sampling and ranking, improving revenue with stable conversion rates.
problem Multi-objective recommendations in online food ordering systems.
method Multi-goal sampling followed by ranking, reducing MO problem to LTR model.
result Significant lift in revenue (2.64%) with stable conversion rates, no drop in last-mile traversal.
Develops hierarchical reinforcement learning value function approximators.
problem Estimating long-term returns in reinforcement learning with multiple goals.
method Introduces hierarchical universal value function approximators (H-UVFAs) using the options framework.
result Demonstrates generalization and improved performance of H-UVFAs over UVFAs.
PCHID improves sample efficiency in reinforcement learning tasks.
problem Sparse rewards make learning policies difficult in reinforcement learning.
method Hindsight Inverse Dynamics with Hindsight Experience Replay and Policy Continuation.
result PCHID significantly improves sample efficiency and final performance on multi-goal tasks.
This paper presents a locally decoupled network parameter learning with local propagation. Three elements are taken into account: (i) sets of nonlinear transforms that describe the representations at all nodes, (ii) a local objective at each node related to the corresponding local representation goal, and (iii) a local…
Deep neural network learns discrete state abstractions for efficient planning.
problem Efficient sequential decision making in large state spaces.
method Information bottleneck method for learning approximate bisimulations using deep neural encoders and action-conditioned HMM.
result Trained method efficiently plans for unseen goals in multi-goal reinforcement learning.
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.
Most reinforcement learning algorithms are inefficient for learning multiple tasks in complex robotic systems, where different tasks share a set of actions. In such environments a compound policy may be learnt with shared neural network parameters, which performs multiple tasks concurrently. However such compound polic…
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.
New neural nets respect triangle inequality, improving graph and reinforcement learning performance.
problem Neural nets lack inductive bias for certain subadditive distances.
method Introduced novel architectures that universally approximate norm-induced metrics.
result Neural nets with triangle inequality inductive bias outperform existing approaches.
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.
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.
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.
MDLdroid improves mobile deep learning for personal sensing with faster training.
problem Continuous local changes and resource constraints in personal mobile sensing affect global model performance.
method ChainSGD-reduce approach to reduce overhead and balance resources.
result 2x to 3.5x faster training on off-the-shelf mobile devices compared to single-device training.