{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/analyzing-policy-distillation-on-multi-task","title":"Analyzing Policy Distillation on Multi-Task Learning and Meta-Reinforcement Learning in Meta-World","arxiv_id":null,"date":"2020-02-08","proceeding":"Preprint 2020 2","authors":["Nathan Blair","Victor Chan and Adarsh Karnati"],"abstract":"Policy distillation partitions a Markov Decision Process into different subsections and learns expert policies  in  each  individual  partition  before  combining them into a single policy for the entire space. Similar to how a sports team has different positions that each con-tribute their own abilities to the team, policy distillation leverages the structure of a Markov Decision Process by first  learning  partition-specific  experts  that  do  not  need to  generalize  as  widely.  When  combined  into  one  global policy,  the  experts  each  contribute  the  learned  features from  their  partitions.  Depending  on  which  part  of  the state space the global policy faces, it can take advantage of the features it has gained from the local policy for that partition.\r\nMeta-reinforcement   learning   and   multi-task   learning   are   very   closely   intertwined   fields.   While   meta-reinforcement  learning  aims  to  quickly  solve  new  tasks based  on  prior  experience,  multi-task  learning  focuses more  on  the  ability  of  an  algorithm  to  generalize  to  a wide  distribution  of  tasks  at  the  same  time.  However,successful meta-learning is typically correlated with better  performance  on  multi-task  learning,  and  vice  versa.An  agent  that  can  quickly  adapt  to  a  new  task  is,  bydefinition, better at learning that new task; similarly, an agent that has generalized to many tasks is likely to learn more quickly when presented with a new but related task.Because  both  meta-learning  and  multi-task  learning  are composed  of  many  individual  tasks,  they  are  naturally propitious  to  partitioning.  Policy  distillation  has  shown promise in multi-task learning, but the results are limited and  not  extensively  studied.  We  explore  the  application of a policy distillation algorithm, Divide-and-Conquer, to the  Meta-World  benchmark.\r\nDivide-and-Conquer (DnC) is a policy distillation algorithm that uses a context to represent information on the partitions of a state space. Based on these contexts, local policies  are  trained  with  KL  divergence  constraints  to keep them similar to one another. They are combined into a  global  policy  with  another  KL  divergence  constraint.\r\nMeta-World is a new benchmark for multi-task learning  and  meta-learning.  We  analyze  DnC’s  performance on   both   the   meta-learning   (ML)   and   the   multi-task learning  (MT)  benchmarks,  using  Trust-Region  Policy Optimization  (TRPO)  as  the  benchmark.  For  the  ML benchmark, we partition the state space by the separate tasks for DnC. During meta-training, we use the training tasks  as  the  partitions  for  DnC  without  the  test  tasks;once we have the final global policy from meta-training,we  apply  it  to  the  test  tasks  to  determine  final  rewards and  success  rates.  For  the  MT  benchmark,  we  again partition the state space by separate tasks. However, there are no held-out tasks–DnC trains on all of the tasks and is tested on them. Each individual task also has variable goal states, so the local policies must learn how to adapt to these variable states. The global policy must not only learn to solve the distinct training tasks, but also it must learn  to  adapt  to  different  goal  states  within  each  task.\r\nWe  find  that  DnC  achieves  the  same  performance  as our  baseline,  TRPO,  on  the  meta-learning  benchmark.When  we  partition  the  state  space  into  the  individual tasks,  the  local  policies  are  able  to  properly  learn  to solve  each  of  the  individual  tasks  successfully  at  a  rate of  around  4-5%.  The  global  policy  composed  of  these individual expert policies has the same performance and success   rate   as   the   local   policies.   On   the   multi-task learning benchmark, DnC achieves success rates around65%. We believe that because DnC is a policy distillation algorithm and multi-task learning test environments have the  same  tasks  in  the  train  and  test  environments,  DnCcan  memorize  each  of  the  individual  tasks  and  perform well  in  all  of  them  at  test  time.  However,  with  meta-learning,  it  is  more  difficult  for  DnC  to  adapt  to  new tasks  at  test  time,  and  therefore  its  performance  is  not nearly  as  good.","url_abs":"https://ncblair.github.io/me/papers.html","url_pdf":"https://ncblair.github.io/me/assets/pdfs/Analyzing_policy_distillation_on_multi-task_learning_and_meta-reinforcement_learning_in_meta-world.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"meta-reinforcement-learning","task_name":"Meta Reinforcement Learning"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[{"method_slug":"trpo","method_name":"TRPO"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/meta-learning-on-ml10","task":"Meta-Learning","dataset":"ML10","model":"DnC","rank_in_archive_order":3,"of":6,"metrics":{"Meta-test success rate":"5.4%"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}