Add to ORKGA common setting in multitask reinforcement learning (RL) demands that an agent rapidly adapt to various stationary reward functions randomly sampled from a fixed distribution. In such situations, the successor representation (SR) is a popular framework which supports rapid policy evaluation by decoupling a policy's expected discounted, cumulative state occupancies from a specific reward function. However, in the natural world, sequential tasks are rarely independent, and instead reflect shifting priorities based on the availability and subjective perception of rewarding stimuli. Reflecting this disjunction, in this paper we study the phenomenon of diminishing marginal utility and introduce a novel state representation, the $\lambda$ repres...
When reinforcement learning is applied with sparse rewards, agents must spend a prohibitively long t...
Reinforcement learning (RL) has developed into a primary approach to learning control strate-gies fo...
A long-standing challenge in reinforcement learning is the design of function approximations and eff...
A common setting in multitask reinforcement learning (RL) demands that an agent rapidly adapt to var...
Successor-style representations have many advantages for reinforcement learning: for example, they c...
In reinforcement learning, temporal difference-based algorithms can be sample-inefficient: for insta...
In this paper we introduce a simple approach for exploration in reinforcement learning (RL) that all...
source code available at https://gitlab.inria.fr/robotlearn/xi_learningTransfer in Reinforcement Lea...
Reinforcement learning (RL) is generally considered as the machine learning answer to the optimal co...
Theories of reward learning in neuroscience have focused on two families of algorithms, thought to c...
A reinforcement-learning agent learns by trying actions and observing resulting reward in each state...
Reinforcement Learning (RL) algorithms allow artificial agents to improve their action selection pol...
In value-based reinforcement learning (RL), unlike in supervised learning, the agent faces not a sin...
We posit a new mechanism for cooperation in multi-agent reinforcement learning (MARL) based upon an...
How inputs are represented is critical for performance in decision-making problems since it determin...
When reinforcement learning is applied with sparse rewards, agents must spend a prohibitively long t...
Reinforcement learning (RL) has developed into a primary approach to learning control strate-gies fo...
A long-standing challenge in reinforcement learning is the design of function approximations and eff...
A common setting in multitask reinforcement learning (RL) demands that an agent rapidly adapt to var...
Successor-style representations have many advantages for reinforcement learning: for example, they c...
In reinforcement learning, temporal difference-based algorithms can be sample-inefficient: for insta...
In this paper we introduce a simple approach for exploration in reinforcement learning (RL) that all...
source code available at https://gitlab.inria.fr/robotlearn/xi_learningTransfer in Reinforcement Lea...
Reinforcement learning (RL) is generally considered as the machine learning answer to the optimal co...
Theories of reward learning in neuroscience have focused on two families of algorithms, thought to c...
A reinforcement-learning agent learns by trying actions and observing resulting reward in each state...
Reinforcement Learning (RL) algorithms allow artificial agents to improve their action selection pol...
In value-based reinforcement learning (RL), unlike in supervised learning, the agent faces not a sin...
We posit a new mechanism for cooperation in multi-agent reinforcement learning (MARL) based upon an...
How inputs are represented is critical for performance in decision-making problems since it determin...
When reinforcement learning is applied with sparse rewards, agents must spend a prohibitively long t...
Reinforcement learning (RL) has developed into a primary approach to learning control strate-gies fo...
A long-standing challenge in reinforcement learning is the design of function approximations and eff...