DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning

• URL: http://arxiv.org/abs/2505.19850v2
• Date: Mon, 20 Oct 2025 12:58:20 GMT
• Title: DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning
• Authors: Leander Diaz-Bone, Marco Bagatella, Jonas Hübotter, Andreas Krause,
• Abstract summary: We propose a method for directed sparse-reward goal-conditioned very long-horizon RL (DISCOVER)<n>We connect DISCOVER to principled exploration in bandits, formally bounding the time until the target task becomes achievable in terms of the agent's initial distance to the target.<n>We find that the directed goal selection of DISCOVER solves exploration problems that are beyond the reach of prior state-of-the-art exploration methods in RL.
• Score: 32.80410217696872
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Sparse-reward reinforcement learning (RL) can model a wide range of highly complex tasks. Solving sparse-reward tasks is RL's core premise, requiring efficient exploration coupled with long-horizon credit assignment, and overcoming these challenges is key for building self-improving agents with superhuman ability. Prior work commonly explores with the objective of solving many sparse-reward tasks, making exploration of individual high-dimensional, long-horizon tasks intractable. We argue that solving such challenging tasks requires solving simpler tasks that are relevant to the target task, i.e., whose achieval will teach the agent skills required for solving the target task. We demonstrate that this sense of direction, necessary for effective exploration, can be extracted from existing RL algorithms, without leveraging any prior information. To this end, we propose a method for directed sparse-reward goal-conditioned very long-horizon RL (DISCOVER), which selects exploratory goals in the direction of the target task. We connect DISCOVER to principled exploration in bandits, formally bounding the time until the target task becomes achievable in terms of the agent's initial distance to the target, but independent of the volume of the space of all tasks. We then perform a thorough evaluation in high-dimensional environments. We find that the directed goal selection of DISCOVER solves exploration problems that are beyond the reach of prior state-of-the-art exploration methods in RL.

Related papers

• Discrete Factorial Representations as an Abstraction for Goal Conditioned Reinforcement Learning [99.38163119531745]
  We show that applying a discretizing bottleneck can improve performance in goal-conditioned RL setups. We experimentally prove the expected return on out-of-distribution goals, while still allowing for specifying goals with expressive structure.
  arXiv  Detail & Related papers  (2022-11-01T03:31:43Z)
• Goal Exploration Augmentation via Pre-trained Skills for Sparse-Reward Long-Horizon Goal-Conditioned Reinforcement Learning [6.540225358657128]
  Reinforcement learning (RL) often struggles to accomplish a sparse-reward long-horizon task in a complex environment. Goal-conditioned reinforcement learning (GCRL) has been employed to tackle this difficult problem via a curriculum of easy-to-reach sub-goals. In GCRL, exploring novel sub-goals is essential for the agent to ultimately find the pathway to the desired goal.
  arXiv  Detail & Related papers  (2022-10-28T11:11:04Z)
• Deep Hierarchical Planning from Pixels [86.14687388689204]
  Director is a method for learning hierarchical behaviors directly from pixels by planning inside the latent space of a learned world model. Despite operating in latent space, the decisions are interpretable because the world model can decode goals into images for visualization. Director also learns successful behaviors across a wide range of environments, including visual control, Atari games, and DMLab levels.
  arXiv  Detail & Related papers  (2022-06-08T18:20:15Z)
• Challenges to Solving Combinatorially Hard Long-Horizon Deep RL Tasks [25.37125069796657]
  We propose a set of tasks which admit many distinct solutions at the high-level, but require reasoning about states and rewards thousands of steps into the future for the best performance. We find that standard RL methods often neglect long-term effects due to discounting, while general-purpose hierarchical RL approaches struggle unless additional abstract domain knowledge can be exploited.
  arXiv  Detail & Related papers  (2022-06-03T20:38:27Z)
• Generalizing to New Tasks via One-Shot Compositional Subgoals [23.15624959305799]
  The ability to generalize to previously unseen tasks with little to no supervision is a key challenge in modern machine learning research. We introduce CASE which attempts to address these issues by training an Imitation Learning agent using adaptive "near future" subgoals. Our experiments show that the proposed approach consistently outperforms the previous state-of-the-art compositional Imitation Learning approach by 30%.
  arXiv  Detail & Related papers  (2022-05-16T14:30:11Z)
• Wish you were here: Hindsight Goal Selection for long-horizon dexterous manipulation [14.901636098553848]
  Solving tasks with a sparse reward in a sample-efficient manner poses a challenge to modern reinforcement learning. Existing strategies explore based on task-agnostic goal distributions, which can render the solution of long-horizon tasks impractical. We extend hindsight relabelling mechanisms to guide exploration along task-specific distributions implied by a small set of successful demonstrations.
  arXiv  Detail & Related papers  (2021-12-01T16:12:32Z)
• Batch Exploration with Examples for Scalable Robotic Reinforcement Learning [63.552788688544254]
  Batch Exploration with Examples (BEE) explores relevant regions of the state-space guided by a modest number of human provided images of important states. BEE is able to tackle challenging vision-based manipulation tasks both in simulation and on a real Franka robot.
  arXiv  Detail & Related papers  (2020-10-22T17:49:25Z)
• Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices [132.49849640628727]
  meta-reinforcement learning (meta-RL) builds agents that can quickly learn new tasks by leveraging prior experience on related tasks. In principle, optimal exploration and exploitation can be learned end-to-end by simply maximizing task performance. We present DREAM, which avoids local optima in end-to-end training, without sacrificing optimal exploration.
  arXiv  Detail & Related papers  (2020-08-06T17:57:36Z)
• Automatic Curriculum Learning through Value Disagreement [95.19299356298876]
  Continually solving new, unsolved tasks is the key to learning diverse behaviors. In the multi-task domain, where an agent needs to reach multiple goals, the choice of training goals can largely affect sample efficiency. We propose setting up an automatic curriculum for goals that the agent needs to solve. We evaluate our method across 13 multi-goal robotic tasks and 5 navigation tasks, and demonstrate performance gains over current state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-06-17T03:58:25Z)
• Planning to Explore via Self-Supervised World Models [120.31359262226758]
  Plan2Explore is a self-supervised reinforcement learning agent. We present a new approach to self-supervised exploration and fast adaptation to new tasks. Without any training supervision or task-specific interaction, Plan2Explore outperforms prior self-supervised exploration methods.
  arXiv  Detail & Related papers  (2020-05-12T17:59:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.