Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 26 for “"Sparse rewards"”.
-
HIERARCHICAL REINFORCEMENT LEARNING WITH PARAMETERIZED OPTIONS FOR LONG-HORIZON ROBOTIC MANIPULATION
… long-horizon robotic manipulation tasks with sparse rewards. In the parameterized options framework of HRL, a high-level policy selects a skill and its corresponding low-level goal parameters from a pre-trained skill library, allowing shared skills across tasks. However, fixed skills can lead …
-
Improving Reaching Tasks of a Simulated Fetch Robot Using Demonstrations along with Hindsight Experience Replay
… Learning (RL). RL heavily relies on rewards to understand its surroundings. Most of the real-world tasks are naturally specified with sparse rewards and finding these rewards becomes extremely difficult as the task horizon and action dimensionality increases. These sparse rewards …
-
A vision based DQN exploration algorithm for collision avoidance
… the challenge is environments inherently have sparse rewards resulting in many actions leading to redundant states. We focus on this problem of learning the dynamics of an unseen environment with sparse rewards more efficiently. To this end, we present an algorithm for improved exploration for …
-
Cooperation and communication in multiagent deep reinforcement learning
… state and action spaces, and sparse rewards? 2) How can multiple Deep Reinforcement Learning agents learn to cooperate in a multiagent setting? To address the first part of this question, this thesis explores the idea of using recurrent neural networks to combat partial …
-
Towards efficient deep reinforcement learning in complex and dynamic tasks
… the DRL faces sampling efficiency problems with sparse rewards in complex and dynamic environments because it requires massive interactions with environments under partial observability. Due to this inefficient data sampling issue, it isn’t easy to train a DRL agent to achieve optimal performance …
-
Side information, robustness, and self supervision in imitation learning
… are oblivious to the possibility of using the sparse rewards provided by the environment, which might guide learning and ease the requirement of access to informative demonstrations. And third, they are oblivious to the fact that, in physically embodied applications, reward functions and …
-
On-policy Object Goal Navigation with Exploration Bonuses
… a priori knowledge of the environment. Given the sparse placement of goals in unknown scenes, exploration is essential for reaching remote objects of interest that are not immediately visible to autonomous agents. Sparse rewards are a crucial problem in reinforcement learning that arises in object …
-
Neural correlates of position, progress, and action during reward-guided sequence navigation in the rat medial prefrontal cortex
… execution of skilled action sequences during sparse rewards necessitates an organization of behavior into modular, temporally extended sub-policies. The rodent Medial Prefrontal Cortex (mPFC) has emerged as a critical brain region implicated in orchestrating such action plans over extended …
-
SPECIFICATION-GUIDED REINFORCEMENT LEARNING
… due to a number of reasons including the use of sparse rewards and lack of compositionality. Furthermore, existing algorithms for verifying neural network controllers (trained using RL) cannot be easily applied to verify controllers for complex long-horizon tasks due to large approximation …
-
Curriculum learning in reinforcement learning for multi-step manipulation tasks
… tasks remain a persistent challenge due to sparse rewards and inefficient exploration. Multi-step manipulation tasks often require precise sequential interactions that are difficult for RL agents to learn effectively. To address this challenge, task decomposition has emerged as an effective …
-
Dynamic Peg-In-Hole Assembly with Effort-Based Collision Detection: Vision-Augmented Reinforcement Learning Control on a Collaborative Robot
… contact and successful insertion, addressing sparse rewards and improving learning robustness. With a validated perception stack, SAC continues to optimize insertion behavior in increasingly dynamic settings. This approach, which avoids dedicated external force or torque sensors, enhances …
-
Adaptive deep reinforcement learning
… exploration techniques in the context of sparse rewards which are essential for many real-world applications. Especially in robotics, crafting a reward function that provides a useful feedback signal in every state proves to be challenging. Instead, it is more pragmatic to signal the …
-
Reinforcement learning with limited prior knowledge in long-term environments
… the learners receive limited observations and sparse feedback, the designer has no control over the environment, and unknown tasks may present at random times to the learner. These features are still challenging for reinforcement learning systems, because the best learning algorithm and the …
-
From Experience to Reasoning: Offline RL Subroutines and LLM-Based Grounding For Sample-Efficient Reinforcement Learning
… particularly in environments characterized by sparse rewards, long horizons, or partial observability. This dissertation investigates how RL agents can learn more efficiently through two complementary forms of guidance: mechanisms derived purely from an agent’s own experience and mechanisms …
-
Training Agents to Achieve Goals
… efficient exploration in long-horizon tasks with sparse rewards. We then leverage vision-language models to ground language instructions in perception, using them as scalable reward functions. Next, to represent the geometric relationships between goals, we present a novel neural network …
-
Fast Decision-making under Time and Resource Constraints
… in systems with long planning horizons and sparse rewards. The belief-space variant of iLQG is applied to the outfielder problem, which may also indicate its applicability to similar target interception problems with input constraints, such as missile defense.
-
A model of functional creativity for generalisation enhancement
… and MiniGrid, a symbolic, discrete domain with sparse rewards and task diversity. In both settings, SETLE-enhanced agents outperformed baseline models in terms of learning speed, generalisation to new goals, and trajectory optimality, validating the practical impact of structured memory and …
-
Electric Bus Charging Scheduling based on Deep Reinforcement Learning
… results validate its efficiency in dealing with sparse rewards and demonstrate improved convergence and cost performance compared to traditional DRL methods. We then extend our HDRL framework to complex multi-bus scenarios characterized by limited charging resources, introducing a Double …
-
Reinforcement learning with temporal logic and causal constraints
… related to unknown subgoal hierarchies and sparse rewards, we introduce a hierarchical RL framework that adopts a novel and simple critic shaping method for accelerating the constraint satisfaction. Then, it is of practical important to train a multi-task agent which generalize to solve an …
-
Comparative Analysis of Intrinsic Reward-Based Reinforcement Learning Algorithms
… learning agents often struggle in tasks with sparse or delayed rewards, since they receive little guidance about which actions to pursue. This thesis investigates how adding intrinsic rewards can help address that issue. We focus on three main methods: Count-Based bonuses, where states are …
Page 1 of 2