Pieter Abbeel, Michael Laskin, Kimin Lee, Aravind Srinivas
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Off-policy deep reinforcement learning (RL) has been successful in a range of challenging domains. However, standard off-policy RL algorithms can suffer from several issues, such as instability in Qlearning and balancing exploration and exploitation. To mitigate these issues, we present SUN-RISE, a simple unified ensemble method, which is compatible with various off-policy RL algorithms. SUNRISE integrates two key ingredients: (a) ensemble-based weighted Bellman backups, which re-weight target Q-values based on uncertainty estimates from a Q-ensemble, and (b) an inference method that selects actions using the highest upper-confidence bounds for efficient exploration. By enforcing the diversity between agents using Bootstrap with random initialization, we show that these different ideas are largely orthogonal and can be fruitfully integrated, together further improving the performance of existing off-policy RL algorithms, such as Soft Actor-Critic and Rainbow DQN, for both continuous and discrete control tasks on both low-dimensional and high-dimensional environments. Our training code is available at https: //github.com/pokaxpoka/sunrise.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2007.04938")
get_code_for_paper("2007.04938")
have("2007.04938")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2007.04938.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2007.04938)
Connect an agent — have() is free.