[Feature Request] MCTS Issue tracker

[vmoens]

• [ ] break_when_all_done in env.rollout() #2355
• [ ] Partial steps in env #2356
  • [ ] BatchedEnv: pass the indices of envs where a step should be done
  • [ ] BatchedEnv: index a BatchedEnv
  • [ ] Stateless env: discard done parts of the TD
• [ ] Scores #2358
  • [x] PUCT (missing tests)
  • [x] UCB (missing tests)
  • [ ] UCB1_TUNED
  • [ ] EXP3
  • [ ] PUCT_VARIANT
• [x] TensorSpec.enumerate()
• [x] Storage
  • [x] Hashing functions #2304
  • [x] Query modules #2305
  • [x] Map #2306
  • [x] MCTSForest #2307
• [ ] Policy classes #2359
  • [ ] MCTSPolicyBase
  • [ ] MCTSPolicy
  • [ ] AlphaGoPolicy
  • [ ] AlphaStarPolicy
  • [ ] MuZeroPolicy

cc @dtsaras @mjlaali